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 2022/05/18 13:33:53 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@99caa6533fde8e7264e6659575c03e5ecf54cd6b)
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 4a3606608 deploying docs (apache/tvm@99caa6533fde8e7264e6659575c03e5ecf54cd6b)
4a3606608 is described below
commit 4a36066088aafd6072e7578613c9b9ed73310079
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Wed May 18 13:33:47 2022 +0000
deploying docs (apache/tvm@99caa6533fde8e7264e6659575c03e5ecf54cd6b)
---
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_paddle.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 18 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 10 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 16 +-
.../tune_conv2d_layer_cuda.rst.txt | 2208 ++++++++++++++++++--
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 138 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 12 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 34 +-
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 12 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../work_with_schedules/sg_execution_times.rst.txt | 18 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 6 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 9 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 56 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 24 +-
.../tutorial/tensor_expr_get_started.rst.txt | 44 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 71 +-
docs/how_to/compile_models/from_paddle.html | 2 +-
docs/how_to/compile_models/from_pytorch.html | 7 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 22 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 17 +-
docs/how_to/deploy_models/deploy_prequantized.html | 6 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 34 +-
docs/how_to/deploy_models/sg_execution_times.html | 18 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 10 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 2208 ++++++++++++++++++--
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 138 +-
.../tune_with_autotvm/sg_execution_times.html | 12 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 34 +-
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 12 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
.../work_with_schedules/sg_execution_times.html | 18 +-
docs/how_to/work_with_schedules/tensorize.html | 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 | 6 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 4 +-
docs/tutorial/autotvm_relay_x86.html | 258 +--
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 24 +-
docs/tutorial/tensor_expr_get_started.html | 44 +-
115 files changed, 4940 insertions(+), 1362 deletions(-)
diff --git a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
index 962240ff1..ec72bf49b 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -98,7 +98,7 @@ In this section, we download a pretrained imagenet model and classify an image.
.. code-block:: none
- Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipff051c63-9567-4d89-bd9a-75d341d3c335 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip3182e83b-cf38-41b7-88e3-d2448c562956 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 ede733a12..935635083 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -100,7 +100,7 @@ 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]
0%| | 16.0k/41.5M [00:00<07:44, 93.6kB/s]
0%| | 48.0k/41.5M [00:00<04:53, 148kB/s]
0%| | 96.0k/41.5M [00:00<03:28, 208kB/s]
0%| | 160k/41.5M [00:00<02:38, 273kB/s]
1%| | 280k/41.5M [00:00<01:41, 427kB/s]
1%|1 | 528k/41.5M [00:01<00:55, 772kB/s]
2%|2 | 0.98M/41.5M [00:01<00:29, 1.43MB/s]
5%|4 | 1.97M/41.5M [00:01<00:14, 2.84MB/s]
8%|8 | 3.50M/41.5M [00:01<00:08, 4.81MB/s]
12%|#2 | 5.03M/41.5M [00:01<00:06, 6.14MB/s]
16%|#5 | 6.56M/41.5M [00:01<00:05, 7.06MB/s]
20%|#9 | 8.09M/41.5M [00:02<00:04, 7.69MB/s]
23%|##3 | 9.62M/41.5M [00:02<00:04, 8.11MB/s]
27%|##6 | 11.1M/41.5M [00:02<00:03, 8.40MB/s]
31%|### | 12.7M/41.5M [00:02<00:03, 8.62MB/s]
34%|###4 | 14.2M/41.5M [00:02<00:03, 8.77MB/s]
38%|###7 | 15.7M/41.5M [00:02<00
:03, 8.88MB/s]
42%|####1 | 17.3M/41.5M [00:03<00:02, 8.96MB/s]
45%|####5 | 18.8M/41.5M [00:03<00:02, 8.99MB/s]
49%|####9 | 20.3M/41.5M [00:03<00:02, 9.03MB/s]
53%|#####2 | 21.9M/41.5M [00:03<00:02, 9.05MB/s]
56%|#####6 | 23.4M/41.5M [00:03<00:02, 9.06MB/s]
60%|###### | 24.9M/41.5M [00:04<00:01, 9.08MB/s]
64%|######3 | 26.4M/41.5M [00:04<00:01, 9.91MB/s]
67%|######7 | 27.9M/41.5M [00:04<00:01, 10.7MB/s]
70%|######9 | 28.9M/41.5M [00:04<00:01, 10.3MB/s]
72%|#######2 | 29.9M/41.5M [00:04<00:01, 8.88MB/s]
75%|#######4 | 31.0M/41.5M [00:04<00:01, 8.13MB/s]
78%|#######8 | 32.5M/41.5M [00:04<00:00, 9.73MB/s]
81%|######## | 33.6M/41.5M [00:05<00:01, 7.28MB/s]
83%|########2 | 34.4M/41.5M [00:05<00:01, 6.61MB/s]
86%|########6 | 35.8M/41.5M [00:05<00:00, 7.23MB/s]
90%|######### | 37.4M/41.5M [00:05<00:00, 7.80MB/s]
94%|#########3| 38.9M/41.5M [00:05<00:00, 8.21MB/s]
97%|####
#####7| 40.4M/41.5M [00:05<00:00, 8.49MB/s]
100%|##########| 41.5M/41.5M [00:05<00:00, 7.26MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
0%| | 16.0k/41.5M [00:00<08:19, 87.1kB/s]
0%| | 48.0k/41.5M [00:00<05:15, 138kB/s]
0%| | 96.0k/41.5M [00:00<03:44, 194kB/s]
0%| | 160k/41.5M [00:00<02:50, 254kB/s]
1%| | 288k/41.5M [00:00<01:44, 412kB/s]
1%|1 | 552k/41.5M [00:01<00:56, 758kB/s]
3%|2 | 1.05M/41.5M [00:01<00:29, 1.43MB/s]
5%|4 | 2.07M/41.5M [00:01<00:14, 2.78MB/s]
9%|8 | 3.55M/41.5M [00:01<00:08, 4.47MB/s]
12%|#2 | 5.02M/41.5M [00:01<00:06, 5.62MB/s]
16%|#5 | 6.50M/41.5M [00:02<00:05, 6.40MB/s]
19%|#9 | 7.98M/41.5M [00:02<00:05, 6.95MB/s]
23%|##2 | 9.45M/41.5M [00:02<00:04, 7.31MB/s]
26%|##6 | 10.9M/41.5M [00:02<00:04, 7.57MB/s]
30%|##9 | 12.4M/41.5M [00:02<00:03, 7.75MB/s]
33%|###3 | 13.9M/41.5M [00:03<00:03, 7.88MB/s]
37%|###6 | 15.3M/41.5M [00:03<00
:03, 7.97MB/s]
41%|#### | 16.8M/41.5M [00:03<00:03, 8.02MB/s]
44%|####4 | 18.3M/41.5M [00:03<00:03, 8.07MB/s]
48%|####7 | 19.8M/41.5M [00:03<00:02, 8.10MB/s]
51%|#####1 | 21.2M/41.5M [00:03<00:02, 8.13MB/s]
55%|#####4 | 22.7M/41.5M [00:04<00:02, 8.14MB/s]
58%|#####8 | 24.2M/41.5M [00:04<00:02, 8.15MB/s]
62%|######1 | 25.7M/41.5M [00:04<00:02, 8.15MB/s]
65%|######5 | 27.1M/41.5M [00:04<00:01, 8.14MB/s]
69%|######8 | 28.6M/41.5M [00:04<00:01, 8.15MB/s]
72%|#######2 | 30.1M/41.5M [00:05<00:01, 8.16MB/s]
76%|#######6 | 31.5M/41.5M [00:05<00:01, 8.17MB/s]
80%|#######9 | 33.0M/41.5M [00:05<00:01, 8.15MB/s]
83%|########3 | 34.5M/41.5M [00:05<00:00, 8.16MB/s]
87%|########6 | 35.9M/41.5M [00:05<00:00, 8.14MB/s]
90%|######### | 37.4M/41.5M [00:06<00:00, 8.14MB/s]
94%|#########3| 38.9M/41.5M [00:06<00:00, 8.16MB/s]
97%|#########7| 40.4M/41.5M [00:06<00:00, 8.16MB/s]
100%|####
######| 41.5M/41.5M [00:06<00:00, 6.72MB/s]
diff --git a/docs/_sources/how_to/compile_models/from_paddle.rst.txt b/docs/_sources/how_to/compile_models/from_paddle.rst.txt
index df334fdb7..8a33abdcb 100644
--- a/docs/_sources/how_to/compile_models/from_paddle.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_paddle.rst.txt
@@ -201,7 +201,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 5.687 seconds)
+ **Total running time of the script:** ( 1 minutes 7.696 seconds)
.. _sphx_glr_download_how_to_compile_models_from_paddle.py:
diff --git a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
index 44e9877ff..ce1939d56 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -79,7 +79,7 @@ Load a pretrained PyTorch model
.. code-block:: none
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
-
0%| | 0.00/44.7M [00:00<?, ?B/s]
14%|#4 | 6.32M/44.7M [00:00<00:00, 66.3MB/s]
28%|##8 | 12.6M/44.7M [00:00<00:00, 62.2MB/s]
85%|########5 | 38.0M/44.7M [00:00<00:00, 152MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 139MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
32%|###2 | 14.5M/44.7M [00:00<00:00, 152MB/s]
79%|#######8 | 35.2M/44.7M [00:00<00:00, 190MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 198MB/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 1c1a2ede3..4f8bb0da3 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -372,7 +372,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 0.705 seconds)
+ **Total running time of the script:** ( 1 minutes 5.671 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 5b0c8737c..1ea205acd 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
@@ -5,15 +5,15 @@
Computation times
=================
-**05:29.449** total execution time for **how_to_compile_models** files:
+**05:41.885** total execution time for **how_to_compile_models** files:
-- **01:05.687**: :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)
-- **01:00.705**: :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``)
-- **00:55.510**: :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)
-- **00:39.947**: :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)
-- **00:30.462**: :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)
-- **00:21.317**: :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)
-- **00:21.104**: :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)
-- **00:19.561**: :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)
-- **00:12.392**: :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)
-- **00:02.765**: :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)
+- **01:07.696**: :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)
+- **01:05.671**: :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``)
+- **00:57.528**: :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)
+- **00:31.436**: :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)
+- **00:30.299**: :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)
+- **00:24.564**: :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)
+- **00:21.668**: :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)
+- **00:21.332**: :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)
+- **00:19.288**: :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)
+- **00:02.402**: :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
index 5297db76f..7ebc6fbc2 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
@@ -393,7 +393,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.4971 16.4501 17.2088 16.1058 0.3300
+ 16.5514 16.4103 17.2285 16.2828 0.3394
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 63ea70ffb..401bb1dbb 100644
--- a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
@@ -108,7 +108,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
.. code-block:: none
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
0%| | 0.00/170M [00:00<?, ?B/s]
11%|#1 | 19.4M/170M [00:00<00:00, 202MB/s]
27%|##6 | 45.7M/170M [00:00<00:00, 245MB/s]
42%|####2 | 71.4M/170M [00:00<00:00, 256MB/s]
57%|#####7 | 97.6M/170M [00:00<00:00, 263MB/s]
73%|#######2 | 124M/170M [00:00<00:00, 267MB/s]
88%|########7 | 149M/170M [00:00<00:00, 256MB/s]
100%|##########| 170M/170M [00:00<00:00, 257MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
10%|# | 17.5M/170M [00:00<00:00, 184MB/s]
25%|##4 | 42.1M/170M [00:00<00:00, 227MB/s]
39%|###9 | 66.9M/170M [00:00<00:00, 242MB/s]
54%|#####3 | 91.5M/170M [00:00<00:00, 248MB/s]
68%|######8 | 116M/170M [00:00<00:00, 249MB/s]
83%|########3 | 141M/170M [00:00<00:00, 254MB/s]
98%|#########7| 166M/170M [00:00<00:00, 257MB/s]
100%|##########| 170M/170M [00:00<00:00, 248MB/s]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -253,7 +253,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 5.179 seconds)
+ **Total running time of the script:** ( 3 minutes 12.717 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 a84e92839..cc25ef8af 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -187,7 +187,7 @@ training. Other models require a full post training calibration.
.. code-block:: none
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
0%| | 0.00/13.6M [00:00<?, ?B/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 168MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 173MB/s]
@@ -344,7 +344,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.4557 90.3198 95.9207 90.0651 0.6082
+ 90.4647 90.3588 92.8938 90.2359 0.3188
@@ -384,7 +384,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 6.114 seconds)
+ **Total running time of the script:** ( 1 minutes 7.477 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 655acd4ac..55ca6da60 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
@@ -351,7 +351,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 118.8269 118.7615 120.3861 118.0224 0.3890
+ 120.2155 120.2355 121.3857 119.3382 0.4114
@@ -385,7 +385,7 @@ Here we give an example of how to measure performance of TVM compiled models.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 5.735 seconds)
+ **Total running time of the script:** ( 1 minutes 52.626 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 a5d1d9077..68124e1e0 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -221,7 +221,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 10.407 seconds)
+ **Total running time of the script:** ( 1 minutes 9.417 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 59075ad5a..de8ba2cfc 100644
--- a/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
@@ -137,7 +137,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
5%|5 | 6952/132723 [00:00<00:01, 69511.95KB/s]
12%|#1 | 15504/132723 [00:00<00:01, 78924.83KB/s]
18%|#8 | 24054/132723 [00:00<00:01, 81924.50KB/s]
25%|##4 | 32546/132723 [00:00<00:01, 83105.03KB/s]
31%|### | 41076/132723 [00:00<00:01, 83893.44KB/s]
37%|###7 | 49649/132723 [00:00<00:00, 84505.47KB/s]
44%|####3 | 58274/132723 [00:00<00:00, 85072.96KB/s]
50%|##### | 66902/132723 [00:00<00:00, 85452.86KB/s]
57%|#####6 | 75453/132723 [00:00<00:00, 85468.01KB/s]
63%|######3 | 84074/132723 [00:01<00:00, 85692.85KB/s]
70%|######9 | 92730/132723 [00:01<00:00, 85956.05KB/s]
76%|#######6 | 101384/132723 [00:01<00:00, 86127.21KB/s]
83%|########2 | 110073/132723 [00:01<00:00, 86353.67KB/s]
89%|########9 | 118709/132723 [00:01<00:00, 86059.40KB/s]
96%|#########5| 127386/132723 [00:01<00:00, 86269.44KB/s]
100%|#######
###| 132723/132723 [00:01<00:00, 84823.44KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
5%|5 | 6933/132723 [00:00<00:01, 69323.29KB/s]
12%|#1 | 15330/132723 [00:00<00:01, 77935.42KB/s]
18%|#7 | 23716/132723 [00:00<00:01, 80633.78KB/s]
24%|##4 | 32107/132723 [00:00<00:01, 81923.65KB/s]
30%|### | 40469/132723 [00:00<00:01, 82531.73KB/s]
37%|###6 | 48818/132723 [00:00<00:01, 82848.61KB/s]
43%|####3 | 57205/132723 [00:00<00:00, 83179.98KB/s]
49%|####9 | 65620/132723 [00:00<00:00, 83487.52KB/s]
56%|#####5 | 73976/132723 [00:00<00:00, 83507.40KB/s]
62%|######2 | 82334/132723 [00:01<00:00, 83527.99KB/s]
68%|######8 | 90694/132723 [00:01<00:00, 83547.13KB/s]
75%|#######4 | 99111/132723 [00:01<00:00, 83734.98KB/s]
81%|########1 | 107612/132723 [00:01<00:00, 84118.68KB/s]
87%|########7 | 116061/132723 [00:01<00:00, 84227.88KB/s]
94%|#########3| 124484/132723 [00:01<00:00, 84218.50KB/s]
100%|########
##| 132723/132723 [00:01<00:00, 82982.41KB/s]
@@ -202,7 +202,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 24.549 seconds)
+ **Total running time of the script:** ( 2 minutes 29.528 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 72e551a84..6c4a7fcb9 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,13 +5,13 @@
Computation times
=================
-**10:42.921** total execution time for **how_to_deploy_models** files:
+**10:43.510** total execution time for **how_to_deploy_models** files:
-- **03:05.179**: :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``)
-- **02:24.549**: :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)
-- **02:05.735**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)
-- **01:10.407**: :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)
-- **01:06.114**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)
-- **00:28.313**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)
-- **00:22.421**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)
-- **00:00.204**: :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``)
+- **03:12.717**: :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``)
+- **02:29.528**: :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)
+- **01:52.626**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)
+- **01:09.417**: :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)
+- **01:07.477**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)
+- **00:29.206**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)
+- **00:22.330**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)
+- **00:00.208**: :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``)
diff --git a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
index a2b71c778..7d186aca2 100644
--- a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
@@ -423,7 +423,7 @@ First let us define two helper functions to get the mobilenet model and a cat im
.. code-block:: none
- Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip8f6aad35-5e5a-4926-b67d-3d9f994e37ee from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipefde4ed6-646f-48db-be3b-a007f0e06a16 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 99a1e1e78..73973d3ae 100644
--- a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
@@ -5,9 +5,9 @@
Computation times
=================
-**00:38.617** total execution time for **how_to_extend_tvm** files:
+**00:38.629** total execution time for **how_to_extend_tvm** files:
-- **00:35.023**: :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``)
-- **00:02.320**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)
-- **00:01.067**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)
-- **00:00.208**: :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``)
+- **00:35.062**: :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``)
+- **00:02.305**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)
+- **00:01.053**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)
+- **00:00.210**: :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``)
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
index 5169ab22e..ee94c9a06 100644
--- a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
@@ -199,10 +199,10 @@ profile the execution time of each passes.
.. code-block:: none
Printing results of timing profile...
- InferType: 5976us [5976us] (45.48%; 45.48%)
- FoldScaleAxis: 7162us [2us] (54.52%; 54.52%)
- FoldConstant: 7160us [1460us] (54.50%; 99.97%)
- InferType: 5700us [5700us] (43.39%; 79.61%)
+ InferType: 6080us [6080us] (45.78%; 45.78%)
+ FoldScaleAxis: 7201us [2us] (54.22%; 54.22%)
+ FoldConstant: 7199us [1477us] (54.21%; 99.97%)
+ InferType: 5722us [5722us] (43.09%; 79.49%)
@@ -239,10 +239,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
.. code-block:: none
Printing results of timing profile...
- InferType: 5761us [5761us] (44.48%; 44.48%)
- FoldScaleAxis: 7192us [2us] (55.52%; 55.52%)
- FoldConstant: 7190us [1518us] (55.51%; 99.97%)
- InferType: 5672us [5672us] (43.79%; 78.89%)
+ InferType: 5825us [5825us] (44.91%; 44.91%)
+ FoldScaleAxis: 7146us [2us] (55.09%; 55.09%)
+ FoldConstant: 7144us [1502us] (55.08%; 99.97%)
+ InferType: 5642us [5642us] (43.50%; 78.98%)
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 4137c03e3..541393c47 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
@@ -295,7 +295,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 46.673771 ms
+ Convolution: 54.145100 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 25eabe685..f7b02417b 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
@@ -628,7 +628,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 6.921626 ms
+ conv2d with tensor core: 6.861769 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 8099c94c3..e091883c1 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -118,8 +118,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.018830
- Baseline: 3.399444
+ Numpy running time: 0.019530
+ Baseline: 3.450291
@@ -210,7 +210,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.308552
+ Opt1: 0.313789
@@ -309,7 +309,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.341195
+ Opt2: 0.346624
@@ -401,7 +401,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.125715
+ Opt3: 0.118491
@@ -520,7 +520,7 @@ flattening.
.. code-block:: none
- Opt4: 0.112148
+ Opt4: 0.111130
@@ -638,7 +638,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111770
+ Opt5: 0.111483
@@ -759,7 +759,7 @@ Futhermore, we can also utilize multi-core processors to do the thread-level par
.. code-block:: none
- Opt6: 0.145485
+ Opt6: 0.145561
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 84a0f324e..0ffec0281 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,8 +5,8 @@
Computation times
=================
-**00:35.347** total execution time for **how_to_optimize_operators** files:
+**00:35.742** total execution time for **how_to_optimize_operators** files:
-- **00:32.707**: :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)
-- **00:01.403**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``)
-- **00:01.236**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)
+- **00:32.981**: :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)
+- **00:01.478**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``)
+- **00:01.283**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
index ea1d7b093..1816aeaa2 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
@@ -5,11 +5,11 @@
Computation times
=================
-**05:04.761** total execution time for **how_to_tune_with_autoscheduler** files:
-
-- **02:27.817**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``)
-- **01:19.903**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)
-- **00:40.543**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)
-- **00:18.839**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)
-- **00:09.046**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)
-- **00:08.613**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)
+**05:02.478** total execution time for **how_to_tune_with_autoscheduler** files:
+
+- **02:25.793**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``)
+- **01:20.595**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)
+- **00:41.396**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)
+- **00:16.701**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)
+- **00:09.128**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)
+- **00:08.864**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
index 6266adc8d..9ae2d50f6 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
@@ -222,11 +222,11 @@ cooperative fetching, unrolling and operator fusion.
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 8;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 56;
allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [648]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [4608]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224 {
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [288]), 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" = 32 {
conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
@@ -241,124 +241,1103 @@ cooperative fetching, unrolling and operator fusion.
conv2d_nchw_1[11] = 0f32
conv2d_nchw_1[12] = 0f32
conv2d_nchw_1[13] = 0f32
- for (rc.outer.outer: int32, 0, 64) {
- let cse_var_2: int32 = (rc.outer.outer*392)
- let cse_var_1: int32 = (rc.outer.outer*72)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [648], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((9 <= floormod(threadIdx.x_1, 81)) && (floormod(threadIdx.x_1, 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv(threadIdx.x_1, 81)*49)) + (floordiv(floormod(threadIdx.x_1, 81), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 224), 81)) && (floormod((threadIdx.x_1 + 62), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 224), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- if @tir.likely((threadIdx.x_1 < 200), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 448), 81)) && (floormod((threadIdx.x_1 + 43), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 448), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 448), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 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, [4608], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 72)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((blockIdx.x*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 28), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((blockIdx.x*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 56), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[((((blockIdx.x*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 84), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((blockIdx.x*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 112), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((blockIdx.x*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 140), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[((((blockIdx.x*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 168), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[((((blockIdx.x*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 196), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((blockIdx.x*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 224), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel[(((((blockIdx.x*294912) + (floordiv(floordiv(threadIdx.x_2, 8), 9)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72)) + 129024)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((blockIdx.x*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 280), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel[((((blockIdx.x*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 308), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[((((blockIdx.x*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 336), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel[((((blockIdx.x*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 364), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel[((((blockIdx.x*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 392), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 3360)] = kernel[((((blockIdx.x*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 420), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 3584)] = kernel[((((blockIdx.x*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 448), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 3808)] = kernel[((((blockIdx.x*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 476), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 4032)] = kernel[(((((blockIdx.x*294912) + (floordiv(floordiv(threadIdx.x_2, 8), 9)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72)) + 258048)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 4256)] = kernel[((((blockIdx.x*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 532), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- if @tir.likely((threadIdx.x_2 < 128), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 4480)] = kernel[((((blockIdx.x*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 560), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
- }
- for (rc.outer.inner: int32, 0, 4) {
- for (rx.outer.inner: int32, 0, 3) {
- for (ff.outer.inner: int32, 0, 2) {
- let cse_var_9: int32 = (ff.outer.inner*7)
- let cse_var_8: int32 = (cse_var_9 + 6)
- let cse_var_7: int32 = (cse_var_9 + 5)
- let cse_var_6: int32 = (cse_var_9 + 4)
- let cse_var_5: int32 = (cse_var_9 + 3)
- let cse_var_4: int32 = (cse_var_9 + 2)
- let cse_var_3: int32 = (cse_var_9 + 1)
- {
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[(((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 3)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 6)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 12)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 15)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 3)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 6)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 12)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 15)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 3)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 6)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 12)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 15)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 3)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 6)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 12)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 15)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 3)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 6)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 12)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 15)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 3)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 6)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 12)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 144)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 15)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 3)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 72)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 6)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 144)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 12)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 153)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 15)]))
- }
+ for (rc.outer.outer: int32, 0, 16) {
+ for (ry.outer.outer: int32, 0, 3) {
+ let cse_var_3: int32 = (rc.outer.outer*1568)
+ let cse_var_2: int32 = (ry.outer.outer*7)
+ let cse_var_1: int32 = (ry.outer.outer*3)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [288], [], scope="shared")[threadIdx.x_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, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[(((((cse_var_3 + (floordiv(threadIdx.x_1, 9)*49)) + cse_var_2) + (floormod(blockIdx.x, 7)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 32)] = @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 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[(((((cse_var_3 + (floordiv((threadIdx.x_1 + 32), 9)*49)) + cse_var_2) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 64)] = @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 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[(((((cse_var_3 + (floordiv((threadIdx.x_1 + 64), 9)*49)) + cse_var_2) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 96)] = @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 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[(((((cse_var_3 + (floordiv((threadIdx.x_1 + 96), 9)*49)) + cse_var_2) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 128)] = @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 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[(((((cse_var_3 + (floordiv((threadIdx.x_1 + 128), 9)*49)) + cse_var_2) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 160)] = @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 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[(((((cse_var_3 + (floordiv((threadIdx.x_1 + 160), 9)*49)) + cse_var_2) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 192)] = @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 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[(((((cse_var_3 + (floordiv((threadIdx.x_1 + 192), 9)*49)) + cse_var_2) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 224)] = @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 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[(((((cse_var_3 + (floordiv((threadIdx.x_1 + 224), 9)*49)) + cse_var_2) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 256)] = @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[(((((cse_var_3 + (floordiv((threadIdx.x_1 + 256), 9)*49)) + cse_var_2) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1: Buffer(kernel.shared, float32, [6144], [], scope="shared")[threadIdx.x_2] = kernel[(((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 32)] = kernel[(((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[(((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 96)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 4608)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 4608)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 160)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 4608)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 9216)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 9216)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 9216)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 288)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 13824)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 13824)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 352)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 13824)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 18432)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 416)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 18432)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 18432)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 480)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 23040)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 23040)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 544)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 23040)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 27648)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 608)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 27648)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 27648)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 32256)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 32256)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 736)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 32256)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 800)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 864)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 41472)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 41472)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 928)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 41472)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 46080)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 992)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 46080)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 46080)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1056)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 50688)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 50688)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 50688)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 55296)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1184)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 55296)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 55296)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1248)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 59904)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 59904)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1312)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 59904)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 64512)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1376)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 64512)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 64512)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1440)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 69120)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 69120)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1504)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 69120)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1632)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 78336)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 78336)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1696)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 78336)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 82944)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1760)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 82944)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 82944)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1824)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 87552)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 87552)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1888)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 87552)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 92160)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1952)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 92160)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 92160)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 96768)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 96768)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2080)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 96768)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 101376)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2144)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 101376)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 101376)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2208)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 105984)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 105984)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2272)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 105984)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2336)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2400)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 115200)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 115200)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 115200)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 119808)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2528)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 119808)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 119808)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2592)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 124416)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 124416)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2656)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 124416)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 129024)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2720)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 129024)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 129024)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2784)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 133632)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 133632)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2848)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 133632)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 138240)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 138240)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 138240)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2976)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 142848)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 142848)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3040)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 142848)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3072)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 147456)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3104)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 147456)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 147456)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3168)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 152064)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3200)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 152064)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3232)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 152064)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3264)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 156672)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3296)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 156672)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3328)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 156672)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3360)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 161280)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3392)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 161280)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3424)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 161280)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3456)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 165888)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3488)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 165888)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3520)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 165888)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3552)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 170496)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3584)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 170496)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3616)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 170496)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3648)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 175104)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3680)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 175104)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3712)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 175104)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3744)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 179712)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3776)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 179712)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3808)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 179712)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3840)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 184320)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3872)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 184320)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3904)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 184320)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3936)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 188928)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3968)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 188928)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4000)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 188928)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4032)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 193536)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4064)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 193536)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4096)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 193536)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4128)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 198144)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4160)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 198144)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4192)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 198144)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4224)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 202752)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4256)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 202752)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4288)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 202752)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4320)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 207360)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4352)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 207360)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4384)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 207360)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4416)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 211968)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4448)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 211968)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4480)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 211968)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4512)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 216576)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4544)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 216576)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4576)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 216576)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4608)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 221184)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4640)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 221184)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4672)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 221184)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4704)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 225792)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4736)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 225792)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4768)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 225792)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4800)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 230400)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4832)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 230400)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4864)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 230400)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4896)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 235008)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4928)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 235008)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4960)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 235008)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4992)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 239616)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5024)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 239616)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5056)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 239616)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5088)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 244224)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5120)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 244224)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5152)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 244224)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5184)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 248832)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5216)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 248832)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5248)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 248832)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5280)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 253440)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5312)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 253440)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5344)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 253440)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5376)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5408)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 258048)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5440)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 258048)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5472)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 262656)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5504)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 262656)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5536)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 262656)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5568)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 267264)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5600)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 267264)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5632)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 267264)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5664)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 271872)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5696)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 271872)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5728)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 271872)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5760)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 276480)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5792)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 276480)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5824)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 276480)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5856)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 281088)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5888)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 281088)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5920)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 281088)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5952)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 285696)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5984)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 285696)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 6016)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 285696)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 6048)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 290304)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 6080)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 290304)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 6112)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 290304)]
+ for (ff.outer.inner: int32, 0, 2) {
+ let cse_var_10: int32 = (ff.outer.inner*7)
+ let cse_var_9: int32 = (cse_var_10 + 6)
+ let cse_var_8: int32 = (cse_var_10 + 5)
+ let cse_var_7: int32 = (cse_var_10 + 4)
+ let cse_var_6: int32 = (cse_var_10 + 3)
+ let cse_var_5: int32 = (cse_var_10 + 2)
+ let cse_var_4: int32 = (cse_var_10 + 1)
+ {
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*192) + (ff.outer.inner*96))]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*192) + (ff.outer.inner*96))]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*192) + (ff.outer.inner*96))]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*192) + (ff.outer.inner*96))]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*192) + (ff.outer.inner*96))]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*192) + (ff.outer.inner*96))]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*192) + (ff.outer.inner*96))]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[1]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 1)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[2]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 1)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[3]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 1)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[4]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 1)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[5]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 1)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[6]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 1)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[7]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 1)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[2]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 2)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[3]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 2)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[4]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 2)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[5]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 2)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[6]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 2)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[7]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 2)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[8]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 2)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[9]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 3)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[10]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 3)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[11]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 3)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[12]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 3)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[13]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 3)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[14]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 3)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[15]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 3)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[10]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 4)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[11]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 4)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[12]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 4)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[13]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 4)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[14]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 4)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[15]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 4)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[16]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 4)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[11]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 5)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[12]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 5)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[13]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 5)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[14]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 5)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[15]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 5)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[16]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 5)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[17]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 5)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[18]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 6)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[19]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 6)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[20]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 6)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[21]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 6)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[22]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 6)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[23]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 6)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[24]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 6)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[19]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 7)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[20]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 7)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[21]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 7)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[22]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 7)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[23]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 7)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[24]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 7)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[25]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 7)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[20]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 8)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[21]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 8)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[22]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 8)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[23]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 8)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[24]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 8)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[25]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 8)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[26]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 8)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[27]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 9)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[28]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 9)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[29]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 9)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[30]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 9)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[31]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 9)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[32]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 9)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[33]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 9)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[28]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 10)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[29]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 10)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[30]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 10)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[31]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 10)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[32]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 10)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[33]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 10)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[34]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 10)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[29]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 11)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[30]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 11)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[31]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 11)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[32]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 11)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[33]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 11)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[34]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 11)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[35]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 11)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[36]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 12)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[37]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 12)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[38]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 12)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[39]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 12)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[40]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 12)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[41]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 12)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[42]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 12)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[37]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 13)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[38]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 13)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[39]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 13)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[40]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 13)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[41]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 13)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[42]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 13)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[43]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 13)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[38]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 14)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[39]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 14)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[40]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 14)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[41]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 14)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[42]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 14)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[43]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 14)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[44]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 14)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[45]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 15)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[46]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 15)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[47]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 15)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[48]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 15)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[49]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 15)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[50]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 15)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[51]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 15)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[46]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 16)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[47]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 16)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[48]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 16)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[49]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 16)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[50]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 16)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[51]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 16)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[52]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 16)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[47]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 17)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[48]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 17)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[49]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 17)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[50]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 17)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[51]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 17)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[52]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 17)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[53]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 17)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[54]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 18)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[55]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 18)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[56]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 18)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[57]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 18)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[58]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 18)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[59]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 18)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[60]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 18)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[55]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 19)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[56]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 19)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[57]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 19)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[58]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 19)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[59]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 19)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[60]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 19)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[61]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 19)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[56]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 20)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[57]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 20)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[58]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 20)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[59]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 20)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[60]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 20)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[61]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 20)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[62]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 20)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[63]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 21)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[64]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 21)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[65]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 21)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[66]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 21)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[67]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 21)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[68]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 21)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[69]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 21)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[64]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 22)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[65]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 22)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[66]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 22)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[67]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 22)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[68]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 22)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[69]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 22)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[70]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 22)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[65]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 23)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[66]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 23)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[67]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 23)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[68]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 23)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[69]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 23)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[70]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 23)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[71]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 23)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[72]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 24)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[73]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 24)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[74]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 24)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[75]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 24)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[76]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 24)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[77]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 24)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[78]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 24)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[73]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 25)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[74]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 25)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[75]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 25)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[76]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 25)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[77]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 25)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[78]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 25)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[79]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 25)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[74]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 26)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[75]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 26)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[76]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 26)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[77]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 26)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[78]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 26)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[79]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 26)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[80]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 26)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[81]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 27)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[82]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 27)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[83]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 27)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[84]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 27)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[85]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 27)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[86]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 27)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[87]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 27)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[82]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 28)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[83]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 28)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[84]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 28)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[85]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 28)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[86]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 28)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[87]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 28)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[88]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 28)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[83]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 29)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[84]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 29)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[85]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 29)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[86]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 29)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[87]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 29)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[88]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 29)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[89]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 29)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[90]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 30)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[91]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 30)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[92]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 30)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[93]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 30)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[94]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 30)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[95]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 30)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[96]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 30)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[91]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 31)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[92]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 31)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[93]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 31)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[94]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 31)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[95]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 31)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[96]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 31)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[97]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 31)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[92]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 32)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[93]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 32)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[94]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 32)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[95]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 32)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[96]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 32)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[97]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 32)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[98]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 32)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[99]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 33)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[100]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 33)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[101]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 33)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[102]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 33)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[103]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 33)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[104]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 33)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[105]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 33)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[100]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 34)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[101]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 34)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[102]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 34)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[103]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 34)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[104]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 34)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[105]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 34)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[106]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 34)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[101]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 35)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[102]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 35)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[103]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 35)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[104]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 35)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[105]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 35)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[106]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 35)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[107]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 35)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[108]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 36)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[109]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 36)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[110]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 36)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[111]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 36)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[112]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 36)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[113]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 36)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[114]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 36)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[109]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 37)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[110]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 37)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[111]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 37)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[112]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 37)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[113]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 37)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[114]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 37)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[115]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 37)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[110]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 38)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[111]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 38)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[112]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 38)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[113]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 38)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[114]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 38)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[115]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 38)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[116]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 38)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[117]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 39)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[118]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 39)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[119]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 39)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[120]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 39)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[121]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 39)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[122]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 39)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[123]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 39)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[118]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 40)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[119]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 40)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[120]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 40)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[121]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 40)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[122]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 40)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[123]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 40)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[124]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 40)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[119]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 41)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[120]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 41)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[121]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 41)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[122]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 41)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[123]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 41)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[124]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 41)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[125]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 41)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[126]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 42)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[127]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 42)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[128]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 42)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[129]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 42)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[130]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 42)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[131]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 42)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[132]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 42)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[127]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 43)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[128]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 43)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[129]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 43)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[130]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 43)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[131]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 43)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[132]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 43)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[133]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 43)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[128]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 44)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[129]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 44)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[130]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 44)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[131]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 44)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[132]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 44)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[133]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 44)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[134]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 44)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[135]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 45)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[136]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 45)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[137]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 45)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[138]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 45)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[139]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 45)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[140]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 45)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[141]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 45)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[136]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 46)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[137]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 46)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[138]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 46)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[139]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 46)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[140]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 46)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[141]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 46)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[142]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 46)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[137]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 47)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[138]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 47)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[139]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 47)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[140]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 47)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[141]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 47)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[142]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 47)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[143]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 47)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[144]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 48)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[145]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 48)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[146]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 48)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[147]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 48)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[148]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 48)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[149]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 48)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[150]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 48)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[145]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 49)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[146]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 49)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[147]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 49)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[148]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 49)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[149]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 49)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[150]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 49)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[151]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 49)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[146]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 50)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[147]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 50)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[148]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 50)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[149]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 50)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[150]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 50)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[151]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 50)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[152]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 50)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[153]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 51)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[154]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 51)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[155]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 51)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[156]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 51)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[157]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 51)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[158]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 51)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[159]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 51)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[154]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 52)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[155]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 52)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[156]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 52)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[157]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 52)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[158]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 52)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[159]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 52)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[160]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 52)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[155]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 53)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[156]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 53)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[157]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 53)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[158]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 53)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[159]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 53)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[160]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 53)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[161]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 53)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[162]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 54)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[163]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 54)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[164]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 54)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[165]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 54)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[166]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 54)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[167]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 54)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[168]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 54)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[163]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 55)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[164]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 55)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[165]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 55)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[166]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 55)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[167]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 55)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[168]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 55)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[169]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 55)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[164]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 56)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[165]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 56)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[166]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 56)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[167]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 56)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[168]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 56)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[169]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 56)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[170]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 56)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[171]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 57)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[172]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 57)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[173]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 57)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[174]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 57)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[175]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 57)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[176]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 57)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[177]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 57)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[172]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 58)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[173]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 58)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[174]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 58)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[175]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 58)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[176]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 58)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[177]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 58)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[178]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 58)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[173]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 59)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[174]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 59)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[175]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 59)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[176]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 59)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[177]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 59)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[178]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 59)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[179]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 59)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[180]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 60)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[181]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 60)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[182]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 60)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[183]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 60)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[184]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 60)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[185]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 60)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[186]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 60)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[181]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 61)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[182]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 61)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[183]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 61)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[184]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 61)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[185]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 61)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[186]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 61)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[187]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 61)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[182]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 62)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[183]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 62)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[184]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 62)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[185]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 62)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[186]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 62)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[187]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 62)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[188]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 62)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[189]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 63)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[190]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 63)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[191]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 63)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[192]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 63)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[193]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 63)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[194]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 63)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[195]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 63)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[190]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 64)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[191]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 64)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[192]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 64)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[193]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 64)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[194]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 64)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[195]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 64)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[196]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 64)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[191]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 65)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[192]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 65)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[193]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 65)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[194]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 65)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[195]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 65)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[196]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 65)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[197]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 65)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[198]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 66)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[199]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 66)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[200]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 66)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[201]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 66)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[202]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 66)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[203]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 66)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[204]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 66)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[199]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 67)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[200]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 67)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[201]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 67)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[202]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 67)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[203]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 67)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[204]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 67)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[205]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 67)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[200]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 68)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[201]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 68)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[202]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 68)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[203]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 68)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[204]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 68)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[205]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 68)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[206]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 68)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[207]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 69)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[208]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 69)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[209]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 69)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[210]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 69)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[211]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 69)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[212]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 69)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[213]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 69)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[208]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 70)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[209]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 70)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[210]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 70)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[211]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 70)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[212]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 70)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[213]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 70)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[214]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 70)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[209]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 71)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[210]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 71)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[211]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 71)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[212]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 71)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[213]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 71)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[214]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 71)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[215]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 71)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[216]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 72)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[217]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 72)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[218]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 72)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[219]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 72)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[220]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 72)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[221]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 72)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[222]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 72)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[217]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 73)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[218]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 73)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[219]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 73)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[220]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 73)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[221]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 73)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[222]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 73)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[223]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 73)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[218]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 74)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[219]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 74)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[220]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 74)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[221]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 74)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[222]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 74)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[223]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 74)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[224]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 74)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[225]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 75)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[226]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 75)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[227]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 75)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[228]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 75)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[229]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 75)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[230]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 75)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[231]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 75)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[226]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 76)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[227]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 76)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[228]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 76)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[229]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 76)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[230]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 76)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[231]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 76)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[232]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 76)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[227]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 77)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[228]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 77)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[229]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 77)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[230]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 77)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[231]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 77)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[232]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 77)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[233]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 77)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[234]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 78)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[235]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 78)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[236]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 78)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[237]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 78)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[238]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 78)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[239]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 78)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[240]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 78)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[235]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 79)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[236]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 79)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[237]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 79)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[238]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 79)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[239]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 79)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[240]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 79)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[241]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 79)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[236]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 80)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[237]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 80)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[238]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 80)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[239]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 80)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[240]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 80)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[241]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 80)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[242]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 80)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[243]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 81)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[244]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 81)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[245]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 81)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[246]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 81)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[247]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 81)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[248]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 81)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[249]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 81)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[244]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 82)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[245]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 82)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[246]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 82)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[247]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 82)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[248]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 82)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[249]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 82)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[250]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 82)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[245]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 83)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[246]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 83)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[247]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 83)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[248]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 83)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[249]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 83)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[250]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 83)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[251]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 83)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[252]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 84)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[253]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 84)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[254]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 84)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[255]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 84)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[256]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 84)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[257]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 84)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[258]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 84)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[253]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 85)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[254]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 85)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[255]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 85)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[256]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 85)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[257]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 85)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[258]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 85)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[259]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 85)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[254]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 86)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[255]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 86)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[256]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 86)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[257]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 86)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[258]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 86)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[259]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 86)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[260]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 86)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[261]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 87)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[262]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 87)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[263]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 87)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[264]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 87)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[265]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 87)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[266]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 87)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[267]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 87)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[262]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 88)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[263]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 88)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[264]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 88)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[265]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 88)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[266]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 88)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[267]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 88)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[268]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 88)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[263]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 89)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[264]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 89)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[265]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 89)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[266]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 89)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[267]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 89)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[268]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 89)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[269]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 89)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[270]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 90)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[271]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 90)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[272]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 90)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[273]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 90)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[274]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 90)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[275]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 90)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[276]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 90)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[271]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 91)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[272]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 91)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[273]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 91)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[274]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 91)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[275]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 91)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[276]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 91)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[277]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 91)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[272]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 92)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[273]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 92)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[274]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 92)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[275]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 92)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[276]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 92)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[277]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 92)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[278]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 92)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[279]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 93)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[280]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 93)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[281]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 93)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[282]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 93)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[283]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 93)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[284]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 93)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[285]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 93)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[280]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 94)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[281]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 94)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[282]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 94)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[283]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 94)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[284]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 94)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[285]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 94)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[286]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 94)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[281]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 95)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[282]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 95)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[283]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 95)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[284]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 95)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[285]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 95)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[286]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 95)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[287]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 95)]))
}
}
}
}
}
for (i1.inner: int32, 0, 2) {
- for (i2.inner: int32, 0, 7) {
- compute[(((((blockIdx.x*3136) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[((i1.inner*7) + i2.inner)] + bias[(((blockIdx.x*64) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+ for (i3.inner: int32, 0, 7) {
+ compute[(((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((floordiv(blockIdx.x, 7)*64) + (threadIdx.x*2)) + i1.inner)]), 0f32)
}
}
}
@@ -412,7 +1391,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.333 ms
+ Execution time of this operator: 0.389 ms
@@ -461,19 +1440,19 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=32)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
- conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=7)
+ conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
- conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
+ conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=7)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
- conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
+ conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=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=3)
+ 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_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
- conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
- conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+ conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
+ conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
@@ -481,11 +1460,11 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
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_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
- compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=7)
+ compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
- compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
- compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
+ compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
+ compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -505,14 +1484,14 @@ 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=32)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=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=32)
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", 64)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -530,10 +1509,10 @@ 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__(32) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[14];
- __shared__ float pad_temp_shared[648];
- __shared__ float kernel_shared[4608];
+ __shared__ float pad_temp_shared[288];
+ __shared__ float kernel_shared[6144];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -548,89 +1527,890 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw[11] = 0.000000e+00f;
conv2d_nchw[12] = 0.000000e+00f;
conv2d_nchw[13] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((9 <= (((int)threadIdx.x) % 81)) && ((((int)threadIdx.x) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((9 <= ((((int)threadIdx.x) + 62) % 81)) && (((((int)threadIdx.x) + 62) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 81) * 49)) + ((((((int)threadIdx.x) + 62) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 200) {
- pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((9 <= ((((int)threadIdx.x) + 43) % 81)) && (((((int)threadIdx.x) + 43) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 448) / 81) * 49)) + ((((((int)threadIdx.x) + 43) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 224) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 8) % 72))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 448) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 672) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 896) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
- kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1120) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 40) % 72))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1344) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1568) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1792) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
- kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72)) + 129024)];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2240) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 8) % 72))];
- kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2464) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2688) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
- kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2912) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3136) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 40) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3360)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3360) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3584)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3584) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3808)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3808) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
- kernel_shared[(((int)threadIdx.x) + 4032)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72)) + 258048)];
- kernel_shared[(((int)threadIdx.x) + 4256)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4256) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 8) % 72))];
- if (((int)threadIdx.x) < 128) {
- kernel_shared[(((int)threadIdx.x) + 4480)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4480) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
- for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
- 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[(((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 3)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 6)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 9)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 12)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 15)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 3)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 6)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 9)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 12)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 15)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 3)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 6)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 9)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 12)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 15)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 3)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 6)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 9)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 12)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 15)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 3)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 6)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 9)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 12)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 15)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 3)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 6)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 9)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 12)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 15)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 3)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 6)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 9)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 12)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 153)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 15)]));
- }
+ for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
+ for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 32)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 32) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 64)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 64) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 96)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 96) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 128)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 128) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 160)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 160) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 192)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 192) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 224) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 256)] = (((((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 * 1568) + (((((int)threadIdx.x) + 256) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 32)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 64)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 96)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 4608)];
+ kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 4608)];
+ kernel_shared[(((int)threadIdx.x) + 160)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 4608)];
+ kernel_shared[(((int)threadIdx.x) + 192)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 9216)];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 9216)];
+ kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 9216)];
+ kernel_shared[(((int)threadIdx.x) + 288)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 13824)];
+ kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 13824)];
+ kernel_shared[(((int)threadIdx.x) + 352)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 13824)];
+ kernel_shared[(((int)threadIdx.x) + 384)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 18432)];
+ kernel_shared[(((int)threadIdx.x) + 416)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 18432)];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 18432)];
+ kernel_shared[(((int)threadIdx.x) + 480)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 23040)];
+ kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 23040)];
+ kernel_shared[(((int)threadIdx.x) + 544)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 23040)];
+ kernel_shared[(((int)threadIdx.x) + 576)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 27648)];
+ kernel_shared[(((int)threadIdx.x) + 608)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 27648)];
+ kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 27648)];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 32256)];
+ kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 32256)];
+ kernel_shared[(((int)threadIdx.x) + 736)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 32256)];
+ kernel_shared[(((int)threadIdx.x) + 768)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 800)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 864)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 41472)];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 41472)];
+ kernel_shared[(((int)threadIdx.x) + 928)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 41472)];
+ kernel_shared[(((int)threadIdx.x) + 960)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 46080)];
+ kernel_shared[(((int)threadIdx.x) + 992)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 46080)];
+ kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 46080)];
+ kernel_shared[(((int)threadIdx.x) + 1056)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 50688)];
+ kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 50688)];
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 50688)];
+ kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 55296)];
+ kernel_shared[(((int)threadIdx.x) + 1184)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 55296)];
+ kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 55296)];
+ kernel_shared[(((int)threadIdx.x) + 1248)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 59904)];
+ kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 59904)];
+ kernel_shared[(((int)threadIdx.x) + 1312)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 59904)];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 1376)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 1440)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 69120)];
+ kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 69120)];
+ kernel_shared[(((int)threadIdx.x) + 1504)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 69120)];
+ kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 1632)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 78336)];
+ kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 78336)];
+ kernel_shared[(((int)threadIdx.x) + 1696)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 78336)];
+ kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 82944)];
+ kernel_shared[(((int)threadIdx.x) + 1760)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 82944)];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 82944)];
+ kernel_shared[(((int)threadIdx.x) + 1824)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 87552)];
+ kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 87552)];
+ kernel_shared[(((int)threadIdx.x) + 1888)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 87552)];
+ kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 92160)];
+ kernel_shared[(((int)threadIdx.x) + 1952)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 92160)];
+ kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 92160)];
+ kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 96768)];
+ kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 96768)];
+ kernel_shared[(((int)threadIdx.x) + 2080)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 96768)];
+ kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 101376)];
+ kernel_shared[(((int)threadIdx.x) + 2144)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 101376)];
+ kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 101376)];
+ kernel_shared[(((int)threadIdx.x) + 2208)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 105984)];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 105984)];
+ kernel_shared[(((int)threadIdx.x) + 2272)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 105984)];
+ kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 2336)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 2400)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 115200)];
+ kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 115200)];
+ kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 115200)];
+ kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 119808)];
+ kernel_shared[(((int)threadIdx.x) + 2528)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 119808)];
+ kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 119808)];
+ kernel_shared[(((int)threadIdx.x) + 2592)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 124416)];
+ kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 124416)];
+ kernel_shared[(((int)threadIdx.x) + 2656)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 124416)];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 129024)];
+ kernel_shared[(((int)threadIdx.x) + 2720)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 129024)];
+ kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 129024)];
+ kernel_shared[(((int)threadIdx.x) + 2784)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 133632)];
+ kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 133632)];
+ kernel_shared[(((int)threadIdx.x) + 2848)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 133632)];
+ kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 138240)];
+ kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 138240)];
+ kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 138240)];
+ kernel_shared[(((int)threadIdx.x) + 2976)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 142848)];
+ kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 142848)];
+ kernel_shared[(((int)threadIdx.x) + 3040)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 142848)];
+ kernel_shared[(((int)threadIdx.x) + 3072)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
+ kernel_shared[(((int)threadIdx.x) + 3104)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 147456)];
+ kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 147456)];
+ kernel_shared[(((int)threadIdx.x) + 3168)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 152064)];
+ kernel_shared[(((int)threadIdx.x) + 3200)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 152064)];
+ kernel_shared[(((int)threadIdx.x) + 3232)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 152064)];
+ kernel_shared[(((int)threadIdx.x) + 3264)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 156672)];
+ kernel_shared[(((int)threadIdx.x) + 3296)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 156672)];
+ kernel_shared[(((int)threadIdx.x) + 3328)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 156672)];
+ kernel_shared[(((int)threadIdx.x) + 3360)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 161280)];
+ kernel_shared[(((int)threadIdx.x) + 3392)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 161280)];
+ kernel_shared[(((int)threadIdx.x) + 3424)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 161280)];
+ kernel_shared[(((int)threadIdx.x) + 3456)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 165888)];
+ kernel_shared[(((int)threadIdx.x) + 3488)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 165888)];
+ kernel_shared[(((int)threadIdx.x) + 3520)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 165888)];
+ kernel_shared[(((int)threadIdx.x) + 3552)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 170496)];
+ kernel_shared[(((int)threadIdx.x) + 3584)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 170496)];
+ kernel_shared[(((int)threadIdx.x) + 3616)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 170496)];
+ kernel_shared[(((int)threadIdx.x) + 3648)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 175104)];
+ kernel_shared[(((int)threadIdx.x) + 3680)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 175104)];
+ kernel_shared[(((int)threadIdx.x) + 3712)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 175104)];
+ kernel_shared[(((int)threadIdx.x) + 3744)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 179712)];
+ kernel_shared[(((int)threadIdx.x) + 3776)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 179712)];
+ kernel_shared[(((int)threadIdx.x) + 3808)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 179712)];
+ kernel_shared[(((int)threadIdx.x) + 3840)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
+ kernel_shared[(((int)threadIdx.x) + 3872)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 184320)];
+ kernel_shared[(((int)threadIdx.x) + 3904)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 184320)];
+ kernel_shared[(((int)threadIdx.x) + 3936)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 188928)];
+ kernel_shared[(((int)threadIdx.x) + 3968)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 188928)];
+ kernel_shared[(((int)threadIdx.x) + 4000)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 188928)];
+ kernel_shared[(((int)threadIdx.x) + 4032)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 193536)];
+ kernel_shared[(((int)threadIdx.x) + 4064)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 193536)];
+ kernel_shared[(((int)threadIdx.x) + 4096)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 193536)];
+ kernel_shared[(((int)threadIdx.x) + 4128)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 198144)];
+ kernel_shared[(((int)threadIdx.x) + 4160)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 198144)];
+ kernel_shared[(((int)threadIdx.x) + 4192)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 198144)];
+ kernel_shared[(((int)threadIdx.x) + 4224)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 202752)];
+ kernel_shared[(((int)threadIdx.x) + 4256)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 202752)];
+ kernel_shared[(((int)threadIdx.x) + 4288)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 202752)];
+ kernel_shared[(((int)threadIdx.x) + 4320)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 207360)];
+ kernel_shared[(((int)threadIdx.x) + 4352)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 207360)];
+ kernel_shared[(((int)threadIdx.x) + 4384)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 207360)];
+ kernel_shared[(((int)threadIdx.x) + 4416)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 211968)];
+ kernel_shared[(((int)threadIdx.x) + 4448)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 211968)];
+ kernel_shared[(((int)threadIdx.x) + 4480)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 211968)];
+ kernel_shared[(((int)threadIdx.x) + 4512)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 216576)];
+ kernel_shared[(((int)threadIdx.x) + 4544)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 216576)];
+ kernel_shared[(((int)threadIdx.x) + 4576)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 216576)];
+ kernel_shared[(((int)threadIdx.x) + 4608)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
+ kernel_shared[(((int)threadIdx.x) + 4640)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 221184)];
+ kernel_shared[(((int)threadIdx.x) + 4672)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 221184)];
+ kernel_shared[(((int)threadIdx.x) + 4704)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 225792)];
+ kernel_shared[(((int)threadIdx.x) + 4736)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 225792)];
+ kernel_shared[(((int)threadIdx.x) + 4768)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 225792)];
+ kernel_shared[(((int)threadIdx.x) + 4800)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 230400)];
+ kernel_shared[(((int)threadIdx.x) + 4832)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 230400)];
+ kernel_shared[(((int)threadIdx.x) + 4864)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 230400)];
+ kernel_shared[(((int)threadIdx.x) + 4896)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 235008)];
+ kernel_shared[(((int)threadIdx.x) + 4928)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 235008)];
+ kernel_shared[(((int)threadIdx.x) + 4960)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 235008)];
+ kernel_shared[(((int)threadIdx.x) + 4992)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 239616)];
+ kernel_shared[(((int)threadIdx.x) + 5024)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 239616)];
+ kernel_shared[(((int)threadIdx.x) + 5056)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 239616)];
+ kernel_shared[(((int)threadIdx.x) + 5088)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 244224)];
+ kernel_shared[(((int)threadIdx.x) + 5120)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 244224)];
+ kernel_shared[(((int)threadIdx.x) + 5152)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 244224)];
+ kernel_shared[(((int)threadIdx.x) + 5184)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 248832)];
+ kernel_shared[(((int)threadIdx.x) + 5216)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 248832)];
+ kernel_shared[(((int)threadIdx.x) + 5248)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 248832)];
+ kernel_shared[(((int)threadIdx.x) + 5280)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 253440)];
+ kernel_shared[(((int)threadIdx.x) + 5312)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 253440)];
+ kernel_shared[(((int)threadIdx.x) + 5344)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 253440)];
+ kernel_shared[(((int)threadIdx.x) + 5376)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
+ kernel_shared[(((int)threadIdx.x) + 5408)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 258048)];
+ kernel_shared[(((int)threadIdx.x) + 5440)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 258048)];
+ kernel_shared[(((int)threadIdx.x) + 5472)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 262656)];
+ kernel_shared[(((int)threadIdx.x) + 5504)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 262656)];
+ kernel_shared[(((int)threadIdx.x) + 5536)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 262656)];
+ kernel_shared[(((int)threadIdx.x) + 5568)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 267264)];
+ kernel_shared[(((int)threadIdx.x) + 5600)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 267264)];
+ kernel_shared[(((int)threadIdx.x) + 5632)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 267264)];
+ kernel_shared[(((int)threadIdx.x) + 5664)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 271872)];
+ kernel_shared[(((int)threadIdx.x) + 5696)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 271872)];
+ kernel_shared[(((int)threadIdx.x) + 5728)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 271872)];
+ kernel_shared[(((int)threadIdx.x) + 5760)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 276480)];
+ kernel_shared[(((int)threadIdx.x) + 5792)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 276480)];
+ kernel_shared[(((int)threadIdx.x) + 5824)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 276480)];
+ kernel_shared[(((int)threadIdx.x) + 5856)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 281088)];
+ kernel_shared[(((int)threadIdx.x) + 5888)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 281088)];
+ kernel_shared[(((int)threadIdx.x) + 5920)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 281088)];
+ kernel_shared[(((int)threadIdx.x) + 5952)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 285696)];
+ kernel_shared[(((int)threadIdx.x) + 5984)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 285696)];
+ kernel_shared[(((int)threadIdx.x) + 6016)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 285696)];
+ kernel_shared[(((int)threadIdx.x) + 6048)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 290304)];
+ kernel_shared[(((int)threadIdx.x) + 6080)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 290304)];
+ kernel_shared[(((int)threadIdx.x) + 6112)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 290304)];
+ __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[0] * kernel_shared[((((int)threadIdx.x) * 192) + (ff_outer_inner * 96))]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 192) + (ff_outer_inner * 96))]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 192) + (ff_outer_inner * 96))]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 192) + (ff_outer_inner * 96))]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 192) + (ff_outer_inner * 96))]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 192) + (ff_outer_inner * 96))]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 192) + (ff_outer_inner * 96))]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[1] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 1)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[2] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 1)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[3] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 1)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[4] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 1)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[5] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 1)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[6] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 1)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[7] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 1)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[2] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 2)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[3] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 2)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[4] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 2)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[5] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 2)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[6] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 2)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[7] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 2)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[8] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 2)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[9] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 3)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[10] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 3)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[11] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 3)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[12] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 3)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[13] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 3)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[14] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 3)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[15] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 3)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[10] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 4)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[11] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 4)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[12] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 4)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[13] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 4)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[14] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 4)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[15] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 4)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[16] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 4)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[11] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 5)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[12] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 5)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[13] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 5)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[14] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 5)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[15] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 5)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[16] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 5)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[17] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 5)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[18] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 6)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[19] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 6)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[20] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 6)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[21] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 6)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[22] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 6)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[23] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 6)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[24] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 6)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[19] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 7)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[20] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 7)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[21] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 7)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[22] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 7)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[23] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 7)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[24] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 7)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[25] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 7)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[20] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 8)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[21] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 8)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[22] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 8)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[23] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 8)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[24] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 8)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[25] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 8)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[26] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 8)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[27] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 9)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[28] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 9)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[29] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 9)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[30] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 9)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[31] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 9)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[32] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 9)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[33] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 9)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[28] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 10)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[29] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 10)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[30] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 10)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[31] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 10)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[32] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 10)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[33] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 10)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[34] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 10)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[29] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 11)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[30] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 11)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[31] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 11)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[32] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 11)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[33] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 11)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[34] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 11)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[35] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 11)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[36] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 12)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[37] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 12)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[38] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 12)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[39] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 12)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[40] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 12)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[41] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 12)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[42] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 12)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[37] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 13)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[38] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 13)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[39] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 13)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[40] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 13)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[41] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 13)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[42] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 13)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[43] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 13)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[38] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 14)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[39] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 14)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[40] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 14)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[41] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 14)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[42] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 14)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[43] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 14)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[44] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 14)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[45] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 15)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[46] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 15)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[47] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 15)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[48] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 15)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[49] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 15)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[50] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 15)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[51] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 15)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[46] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 16)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[47] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 16)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[48] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 16)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[49] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 16)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[50] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 16)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[51] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 16)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[52] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 16)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[47] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 17)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[48] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 17)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[49] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 17)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[50] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 17)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[51] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 17)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[52] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 17)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[53] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 17)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[54] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 18)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[55] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 18)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[56] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 18)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[57] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 18)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[58] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 18)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[59] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 18)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[60] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 18)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[55] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 19)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[56] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 19)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[57] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 19)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[58] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 19)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[59] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 19)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[60] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 19)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[61] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 19)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[56] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 20)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[57] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 20)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[58] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 20)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[59] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 20)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[60] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 20)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[61] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 20)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[62] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 20)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[63] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 21)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[64] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 21)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[65] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 21)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[66] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 21)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[67] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 21)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[68] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 21)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[69] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 21)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[64] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 22)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[65] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 22)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[66] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 22)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[67] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 22)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[68] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 22)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[69] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 22)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[70] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 22)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[65] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 23)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[66] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 23)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[67] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 23)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[68] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 23)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[69] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 23)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[70] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 23)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[71] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 23)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[72] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 24)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[73] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 24)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[74] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 24)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[75] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 24)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[76] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 24)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[77] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 24)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[78] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 24)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[73] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 25)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[74] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 25)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[75] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 25)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[76] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 25)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[77] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 25)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[78] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 25)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[79] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 25)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[74] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 26)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[75] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 26)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[76] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 26)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[77] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 26)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[78] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 26)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[79] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 26)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[80] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 26)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[81] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 27)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[82] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 27)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[83] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 27)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[84] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 27)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[85] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 27)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[86] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 27)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[87] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 27)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[82] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 28)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[83] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 28)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[84] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 28)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[85] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 28)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[86] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 28)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[87] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 28)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[88] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 28)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[83] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 29)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[84] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 29)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[85] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 29)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[86] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 29)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[87] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 29)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[88] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 29)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[89] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 29)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[90] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 30)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[91] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 30)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[92] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 30)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[93] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 30)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[94] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 30)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[95] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 30)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[96] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 30)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[91] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 31)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[92] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 31)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[93] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 31)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[94] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 31)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[95] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 31)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[96] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 31)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[97] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 31)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[92] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 32)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[93] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 32)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[94] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 32)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[95] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 32)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[96] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 32)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[97] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 32)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[98] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 32)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[99] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 33)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[100] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 33)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[101] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 33)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[102] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 33)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[103] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 33)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[104] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 33)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[105] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 33)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[100] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 34)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[101] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 34)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[102] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 34)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[103] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 34)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[104] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 34)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[105] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 34)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[106] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 34)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[101] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 35)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[102] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 35)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[103] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 35)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[104] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 35)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[105] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 35)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[106] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 35)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[107] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 35)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[108] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 36)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[109] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 36)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[110] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 36)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[111] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 36)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[112] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 36)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[113] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 36)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[114] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 36)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[109] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 37)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[110] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 37)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[111] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 37)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[112] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 37)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[113] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 37)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[114] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 37)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[115] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 37)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[110] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 38)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[111] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 38)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[112] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 38)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[113] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 38)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[114] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 38)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[115] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 38)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[116] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 38)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[117] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 39)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[118] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 39)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[119] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 39)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[120] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 39)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[121] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 39)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[122] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 39)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[123] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 39)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[118] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 40)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[119] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 40)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[120] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 40)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[121] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 40)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[122] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 40)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[123] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 40)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[124] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 40)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[119] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 41)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[120] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 41)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[121] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 41)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[122] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 41)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[123] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 41)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[124] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 41)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[125] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 41)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[126] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 42)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[127] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 42)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[128] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 42)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[129] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 42)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[130] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 42)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[131] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 42)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[132] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 42)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[127] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 43)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[128] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 43)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[129] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 43)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[130] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 43)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[131] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 43)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[132] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 43)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[133] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 43)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[128] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 44)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[129] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 44)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[130] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 44)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[131] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 44)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[132] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 44)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[133] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 44)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[134] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 44)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[135] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 45)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[136] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 45)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[137] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 45)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[138] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 45)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[139] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 45)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[140] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 45)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[141] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 45)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[136] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 46)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[137] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 46)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[138] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 46)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[139] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 46)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[140] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 46)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[141] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 46)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[142] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 46)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[137] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 47)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[138] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 47)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[139] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 47)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[140] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 47)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[141] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 47)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[142] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 47)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[143] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 47)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[144] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 48)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[145] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 48)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[146] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 48)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[147] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 48)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[148] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 48)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[149] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 48)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[150] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 48)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[145] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 49)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[146] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 49)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[147] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 49)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[148] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 49)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[149] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 49)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[150] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 49)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[151] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 49)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[146] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 50)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[147] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 50)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[148] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 50)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[149] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 50)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[150] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 50)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[151] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 50)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[152] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 50)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[153] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 51)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[154] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 51)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[155] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 51)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[156] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 51)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[157] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 51)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[158] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 51)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[159] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 51)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[154] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 52)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[155] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 52)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[156] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 52)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[157] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 52)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[158] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 52)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[159] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 52)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[160] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 52)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[155] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 53)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[156] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 53)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[157] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 53)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[158] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 53)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[159] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 53)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[160] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 53)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[161] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 53)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[162] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 54)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[163] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 54)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[164] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 54)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[165] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 54)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[166] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 54)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[167] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 54)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[168] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 54)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[163] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 55)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[164] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 55)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[165] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 55)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[166] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 55)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[167] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 55)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[168] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 55)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[169] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 55)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[164] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 56)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[165] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 56)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[166] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 56)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[167] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 56)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[168] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 56)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[169] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 56)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[170] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 56)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[171] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 57)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[172] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 57)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[173] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 57)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[174] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 57)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[175] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 57)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[176] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 57)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[177] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 57)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[172] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 58)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[173] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 58)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[174] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 58)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[175] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 58)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[176] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 58)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[177] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 58)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[178] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 58)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[173] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 59)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[174] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 59)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[175] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 59)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[176] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 59)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[177] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 59)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[178] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 59)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[179] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 59)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[180] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 60)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[181] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 60)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[182] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 60)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[183] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 60)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[184] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 60)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[185] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 60)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[186] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 60)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[181] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 61)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[182] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 61)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[183] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 61)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[184] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 61)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[185] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 61)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[186] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 61)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[187] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 61)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[182] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 62)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[183] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 62)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[184] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 62)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[185] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 62)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[186] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 62)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[187] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 62)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[188] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 62)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[189] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 63)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[190] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 63)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[191] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 63)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[192] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 63)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[193] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 63)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[194] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 63)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[195] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 63)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[190] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 64)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[191] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 64)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[192] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 64)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[193] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 64)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[194] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 64)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[195] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 64)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[196] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 64)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[191] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 65)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[192] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 65)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[193] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 65)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[194] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 65)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[195] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 65)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[196] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 65)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[197] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 65)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[198] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 66)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[199] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 66)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[200] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 66)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[201] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 66)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[202] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 66)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[203] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 66)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[204] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 66)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[199] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 67)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[200] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 67)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[201] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 67)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[202] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 67)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[203] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 67)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[204] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 67)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[205] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 67)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[200] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 68)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[201] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 68)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[202] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 68)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[203] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 68)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[204] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 68)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[205] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 68)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[206] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 68)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[207] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 69)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[208] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 69)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[209] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 69)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[210] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 69)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[211] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 69)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[212] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 69)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[213] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 69)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[208] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 70)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[209] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 70)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[210] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 70)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[211] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 70)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[212] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 70)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[213] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 70)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[214] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 70)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[209] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 71)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[210] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 71)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[211] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 71)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[212] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 71)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[213] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 71)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[214] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 71)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[215] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 71)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[216] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 72)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[217] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 72)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[218] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 72)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[219] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 72)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[220] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 72)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[221] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 72)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[222] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 72)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[217] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 73)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[218] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 73)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[219] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 73)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[220] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 73)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[221] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 73)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[222] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 73)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[223] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 73)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[218] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 74)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[219] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 74)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[220] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 74)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[221] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 74)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[222] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 74)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[223] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 74)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[224] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 74)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[225] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 75)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[226] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 75)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[227] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 75)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[228] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 75)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[229] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 75)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[230] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 75)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[231] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 75)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[226] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 76)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[227] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 76)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[228] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 76)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[229] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 76)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[230] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 76)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[231] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 76)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[232] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 76)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[227] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 77)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[228] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 77)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[229] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 77)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[230] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 77)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[231] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 77)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[232] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 77)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[233] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 77)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[234] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 78)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[235] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 78)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[236] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 78)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[237] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 78)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[238] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 78)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[239] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 78)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[240] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 78)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[235] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 79)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[236] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 79)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[237] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 79)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[238] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 79)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[239] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 79)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[240] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 79)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[241] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 79)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[236] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 80)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[237] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 80)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[238] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 80)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[239] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 80)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[240] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 80)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[241] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 80)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[242] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 80)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[243] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 81)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[244] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 81)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[245] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 81)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[246] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 81)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[247] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 81)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[248] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 81)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[249] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 81)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[244] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 82)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[245] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 82)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[246] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 82)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[247] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 82)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[248] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 82)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[249] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 82)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[250] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 82)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[245] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 83)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[246] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 83)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[247] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 83)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[248] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 83)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[249] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 83)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[250] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 83)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[251] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 83)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[252] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 84)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[253] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 84)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[254] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 84)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[255] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 84)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[256] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 84)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[257] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 84)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[258] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 84)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[253] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 85)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[254] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 85)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[255] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 85)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[256] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 85)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[257] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 85)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[258] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 85)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[259] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 85)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[254] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 86)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[255] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 86)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[256] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 86)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[257] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 86)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[258] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 86)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[259] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 86)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[260] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 86)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[261] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 87)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[262] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 87)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[263] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 87)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[264] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 87)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[265] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 87)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[266] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 87)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[267] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 87)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[262] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 88)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[263] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 88)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[264] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 88)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[265] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 88)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[266] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 88)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[267] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 88)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[268] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 88)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[263] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 89)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[264] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 89)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[265] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 89)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[266] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 89)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[267] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 89)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[268] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 89)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[269] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 89)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[270] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 90)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[271] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 90)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[272] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 90)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[273] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 90)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[274] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 90)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[275] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 90)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[276] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 90)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[271] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 91)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[272] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 91)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[273] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 91)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[274] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 91)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[275] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 91)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[276] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 91)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[277] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 91)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[272] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 92)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[273] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 92)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[274] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 92)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[275] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 92)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[276] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 92)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[277] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 92)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[278] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 92)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[279] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 93)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[280] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 93)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[281] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 93)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[282] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 93)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[283] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 93)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[284] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 93)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[285] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 93)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[280] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 94)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[281] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 94)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[282] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 94)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[283] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 94)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[284] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 94)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[285] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 94)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[286] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 94)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[281] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 95)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[282] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 95)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[283] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 95)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[284] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 95)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[285] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 95)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[286] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 95)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[287] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 95)]));
}
}
}
for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
- compute[(((((((int)blockIdx.x) * 3136) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[((i1_inner * 7) + i2_inner)] + bias[(((((int)blockIdx.x) * 64) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
+ compute[((((((((int)blockIdx.x) / 7) * 3136) + (((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) * 64) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
}
}
}
@@ -690,7 +2470,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 27.817 seconds)
+ **Total running time of the script:** ( 2 minutes 25.793 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 119955f55..ed2c0938f 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -614,7 +614,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 9.5788 9.5924 9.6194 9.5246 0.0399
+ 9.9809 9.9759 10.0159 9.9508 0.0268
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 8ed18df20..6e8701286 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
@@ -633,7 +633,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 775.9427 776.4630 778.8285 772.5366 2.5949
+ 764.2532 762.7735 768.1185 761.8676 2.7581
@@ -658,7 +658,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 19.903 seconds)
+ **Total running time of the script:** ( 1 minutes 20.595 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 3a5e5af19..4b68ea3ba 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
@@ -362,74 +362,80 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], [])} {
- for (i0.outer: int32, 0, 16) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [128]), storage_scope = global;
- for (i1.outer: int32, 0, 32) {
- for (i.inner.init: int32, 0, 8) {
- let cse_var_1: int32 = (i.inner.init*16)
- {
- compute_5: Buffer(compute_4, float32, [128], [])[cse_var_1] = 0f32
- compute_5[(cse_var_1 + 1)] = 0f32
- compute_5[(cse_var_1 + 2)] = 0f32
- compute_5[(cse_var_1 + 3)] = 0f32
- compute_5[(cse_var_1 + 4)] = 0f32
- compute_5[(cse_var_1 + 5)] = 0f32
- compute_5[(cse_var_1 + 6)] = 0f32
- compute_5[(cse_var_1 + 7)] = 0f32
- compute_5[(cse_var_1 + 8)] = 0f32
- compute_5[(cse_var_1 + 9)] = 0f32
- compute_5[(cse_var_1 + 10)] = 0f32
- compute_5[(cse_var_1 + 11)] = 0f32
- compute_5[(cse_var_1 + 12)] = 0f32
- compute_5[(cse_var_1 + 13)] = 0f32
- compute_5[(cse_var_1 + 14)] = 0f32
- compute_5[(cse_var_1 + 15)] = 0f32
- }
- }
- for (elem_idx: int32, 0, (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])) {
- for (i.inner: int32, 0, 8) {
- let cse_var_19: int32 = (i.inner*16)
- let cse_var_18: int32 = (elem_idx*16)
- let cse_var_17: int32 = (cse_var_19 + 1)
- let cse_var_16: int32 = (cse_var_19 + 11)
- let cse_var_15: int32 = (cse_var_19 + 12)
- let cse_var_14: int32 = (cse_var_19 + 13)
- let cse_var_13: int32 = (cse_var_19 + 14)
- let cse_var_12: int32 = (cse_var_19 + 15)
- let cse_var_11: int32 = (cse_var_19 + 2)
- let cse_var_10: int32 = (cse_var_19 + 3)
- let cse_var_9: int32 = (cse_var_19 + 4)
- let cse_var_8: int32 = (cse_var_19 + 5)
- let cse_var_7: int32 = (cse_var_19 + 6)
- let cse_var_6: int32 = (cse_var_19 + 7)
- let cse_var_5: int32 = (cse_var_19 + 8)
- let cse_var_4: int32 = (cse_var_19 + 9)
- let cse_var_3: int32 = (cse_var_19 + 10)
- let cse_var_2: int32 = ((i0.outer*2048) + (i.inner*256))
- {
- compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[((placeholder_3[i1.outer]*16) + cse_var_18)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 1)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 2)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 3)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 4)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 5)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 6)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 7)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 8)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 9)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 10)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 11)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 12)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 13)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 14)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 15)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
+ preflattened_buffer_map = {placeholder_8: placeholder_15: Buffer(placeholder_13, int32, [33], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 32) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 8) {
+ for (nb_j.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 8) {
+ let cse_var_1: int32 = (((i.outer.inner*256) + (i.inner.init*32)) + (nb_j.inner*16))
+ {
+ compute_5: Buffer(compute_4, float32, [2048], [])[cse_var_1] = 0f32
+ compute_5[(cse_var_1 + 1)] = 0f32
+ compute_5[(cse_var_1 + 2)] = 0f32
+ compute_5[(cse_var_1 + 3)] = 0f32
+ compute_5[(cse_var_1 + 4)] = 0f32
+ compute_5[(cse_var_1 + 5)] = 0f32
+ compute_5[(cse_var_1 + 6)] = 0f32
+ compute_5[(cse_var_1 + 7)] = 0f32
+ compute_5[(cse_var_1 + 8)] = 0f32
+ compute_5[(cse_var_1 + 9)] = 0f32
+ compute_5[(cse_var_1 + 10)] = 0f32
+ compute_5[(cse_var_1 + 11)] = 0f32
+ compute_5[(cse_var_1 + 12)] = 0f32
+ compute_5[(cse_var_1 + 13)] = 0f32
+ compute_5[(cse_var_1 + 14)] = 0f32
+ compute_5[(cse_var_1 + 15)] = 0f32
+ }
+ }
+ for (elem_idx: int32, 0, let cse_var_2: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
+ for (i.inner: int32, 0, 8) {
+ let cse_var_21: int32 = (elem_idx*16)
+ let cse_var_20: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
+ let cse_var_19: int32 = (((i.outer.inner*256) + (i.inner*32)) + (nb_j.inner*16))
+ let cse_var_18: int32 = (cse_var_19 + 1)
+ let cse_var_17: int32 = (cse_var_19 + 11)
+ let cse_var_16: int32 = (cse_var_19 + 12)
+ let cse_var_15: int32 = (cse_var_19 + 13)
+ let cse_var_14: int32 = (cse_var_19 + 14)
+ let cse_var_13: int32 = (cse_var_19 + 15)
+ let cse_var_12: int32 = (cse_var_19 + 2)
+ let cse_var_11: int32 = (cse_var_19 + 3)
+ let cse_var_10: int32 = (cse_var_19 + 4)
+ let cse_var_9: int32 = (cse_var_19 + 5)
+ let cse_var_8: int32 = (cse_var_19 + 6)
+ let cse_var_7: int32 = (cse_var_19 + 7)
+ let cse_var_6: int32 = (cse_var_19 + 8)
+ let cse_var_5: int32 = (cse_var_19 + 9)
+ let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i.outer.inner*2048)) + (i.inner*256))
+ let cse_var_3: int32 = (cse_var_19 + 10)
+ {
+ compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[((placeholder_3[cse_var_20]*16) + cse_var_21)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ }
+ }
}
}
}
- for (i0.inner: int32, 0, 8) {
- let cse_var_20: int32 = (((i0.outer*4096) + (i0.inner*512)) + (i1.outer*16))
- compute[ramp(cse_var_20, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_20, 1, 16)]), broadcast(0f32, 16))
+ for (i0.inner: int32, 0, 64) {
+ for (i1.inner: int32, 0, 32) {
+ let cse_var_22: int32 = ((((floordiv(i0.outer.i1.outer.fused, 16)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32)) + i1.inner)
+ compute[cse_var_22] = max((compute_5[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_22]), 0f32)
+ }
}
}
}
@@ -483,7 +489,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.829 ms
+ Execution time of this operator: 1.842 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 2789d42c4..9f98cf9c2 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:44.112** total execution time for **how_to_tune_with_autotvm** files:
+**00:45.054** total execution time for **how_to_tune_with_autotvm** files:
-- **00:43.196**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)
-- **00:00.240**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)
-- **00:00.229**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``)
-- **00:00.226**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``)
-- **00:00.223**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``)
+- **00:44.125**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)
+- **00:00.246**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)
+- **00:00.229**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``)
+- **00:00.227**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``)
+- **00:00.227**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``)
diff --git a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
index ec8bc73f6..c10753b4c 100644
--- a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
@@ -859,8 +859,8 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2885496
- No: 6 GFLOPS: 42.39/42.39 result: MeasureResult(costs=(0.005461852578947368,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6047112941741943, timestamp=1652876750.7511399) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
- No: 7 GFLOPS: 0.00/42.39 result: Traceback (most recent call last):
+ No: 6 GFLOPS: 92.93/92.93 result: MeasureResult(costs=(0.0024911723958333334,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6307353973388672, timestamp=1652876930.0346053) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
+ No: 7 GFLOPS: 0.00/92.93 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -983,7 +983,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6225319
- No: 8 GFLOPS: 0.00/42.39 result: Traceback (most recent call last):
+ No: 8 GFLOPS: 0.00/92.93 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1106,7 +1106,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,943546
- No: 9 GFLOPS: 0.00/42.39 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 0.00/92.93 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1229,7 +1229,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2868708
- No: 10 GFLOPS: 0.00/42.39 result: Traceback (most recent call last):
+ No: 10 GFLOPS: 0.00/92.93 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
res = future.result()
File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
@@ -1247,7 +1247,7 @@ for this template
TimeoutError
[('tile_f', [-1, 32, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4691833
- No: 11 GFLOPS: 0.00/42.39 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 0.00/92.93 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1370,7 +1370,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1042124
- No: 12 GFLOPS: 0.00/42.39 result: Traceback (most recent call last):
+ No: 12 GFLOPS: 0.00/92.93 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1493,7 +1493,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10013405
- No: 13 GFLOPS: 0.00/42.39 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/92.93 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1616,7 +1616,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6732082
- No: 14 GFLOPS: 0.00/42.39 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/92.93 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1739,7 +1739,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7536735
- No: 15 GFLOPS: 0.00/42.39 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 0.00/92.93 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1862,7 +1862,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,482121
- No: 16 GFLOPS: 0.00/42.39 result: Traceback (most recent call last):
+ No: 16 GFLOPS: 0.00/92.93 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1985,7 +1985,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2824525
- No: 17 GFLOPS: 0.00/42.39 result: Traceback (most recent call last):
+ No: 17 GFLOPS: 0.00/92.93 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2108,7 +2108,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4559286
- No: 18 GFLOPS: 0.00/42.39 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 0.00/92.93 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2231,7 +2231,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9677544
- No: 19 GFLOPS: 0.00/42.39 result: Traceback (most recent call last):
+ No: 19 GFLOPS: 0.00/92.93 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 721, in __call__
yield remote, remote.load_module(os.path.split(build_result.filename)[1])
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 685, in run_through_rpc
@@ -2319,7 +2319,7 @@ for this template
15: _PyEval_EvalFrameDefault
14: 0x0000000000537c30
13: _PyObject_FastCallKeywords
- 12: 0x00007f7253a78fa2
+ 12: 0x00007fce3ecc1fa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -2384,7 +2384,7 @@ for this template
21: _PyFunction_FastCallKeywords
20: _PyEval_EvalFrameDefault
19: _PyFunction_FastCall [('tile_f', [-1, 8, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6390073
- No: 20 GFLOPS: 143.67/143.67 result: MeasureResult(costs=(0.0016113597301587303,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1335551738739014, timestamp=1652876776.9256022) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
+ No: 20 GFLOPS: 143.43/143.43 result: MeasureResult(costs=(0.00161398642,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.435722827911377, timestamp=1652876955.858234) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
@@ -2437,7 +2437,7 @@ and measure running time.
Best config:
[('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
- Time cost of this operator: 0.001995
+ Time cost of this operator: 0.001988
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 5d07cf956..209e1497e 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
@@ -292,10 +292,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 501.9 99.098 (1, 2, 10, 10, 3) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.466 0.684 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 1.101 0.217 (1, 1, 10, 10, 3) 1 1
- Total_time - 506.467 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 314.1 98.755 (1, 2, 10, 10, 3) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.058 0.961 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.901 0.283 (1, 1, 10, 10, 3) 1 1
+ Total_time - 318.058 - - - -
@@ -357,10 +357,10 @@ Timing the tuned program
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 80.75 96.809 (1, 6, 10, 10, 1) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.753 2.102 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.908 1.089 (1, 1, 10, 10, 3) 1 1
- Total_time - 83.412 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 80.75 96.855 (1, 6, 10, 10, 1) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.702 2.041 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.92 1.104 (1, 1, 10, 10, 3) 1 1
+ Total_time - 83.372 - - - -
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 a54595e58..5bcf3cda0 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:46.852** total execution time for **how_to_work_with_microtvm** files:
+**00:48.029** total execution time for **how_to_work_with_microtvm** files:
-- **00:42.591**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)
-- **00:03.646**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)
-- **00:00.213**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``)
-- **00:00.202**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.py``)
-- **00:00.200**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tvmc.py` (``micro_tvmc.py``)
+- **00:43.672**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)
+- **00:03.732**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)
+- **00:00.222**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tvmc.py` (``micro_tvmc.py``)
+- **00:00.204**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``)
+- **00:00.198**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.py``)
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index 3841777f8..c8a387657 100644
--- a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
@@ -5,8 +5,8 @@
Computation times
=================
-**00:08.896** total execution time for **how_to_work_with_relay** files:
+**00:08.906** total execution time for **how_to_work_with_relay** files:
-- **00:06.798**: :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)
-- **00:01.877**: :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)
-- **00:00.221**: :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``)
+- **00:06.834**: :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)
+- **00:01.845**: :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)
+- **00:00.228**: :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``)
diff --git a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
index 1559c2210..0f3c499d9 100644
--- a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
@@ -5,13 +5,13 @@
Computation times
=================
-**00:05.747** total execution time for **how_to_work_with_schedules** files:
+**00:05.823** total execution time for **how_to_work_with_schedules** files:
-- **00:02.099**: :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)
-- **00:01.153**: :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)
-- **00:00.743**: :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)
-- **00:00.715**: :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)
-- **00:00.313**: :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)
-- **00:00.252**: :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``)
-- **00:00.242**: :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)
-- **00:00.230**: :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``)
+- **00:02.130**: :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)
+- **00:01.156**: :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)
+- **00:00.745**: :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)
+- **00:00.733**: :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)
+- **00:00.320**: :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)
+- **00:00.254**: :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``)
+- **00:00.251**: :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)
+- **00:00.233**: :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``)
diff --git a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
index ef5f5684e..79b996684 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -318,7 +318,7 @@ The importing needs to happen before the tensorized GEMV being executed.
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp_3e83st1/input0.cc'\nsource_filename = \"/tmp/tmp_3e83st1/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/tmpr5uifka1/input0.cc'\nsource_filename = \"/tmp/tmpr5uifka1/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 b1b7077c7..bac4b54b5 100644
--- a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
@@ -5,7 +5,7 @@
Computation times
=================
-**00:20.828** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:20.872** total execution time for **topic_vta_tutorials_autotvm** files:
-- **00:20.618**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``)
-- **00:00.210**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``)
+- **00:20.664**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``)
+- **00:00.208**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``)
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
index 5ff41041d..04129d058 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -265,7 +265,7 @@ The compilation steps are:
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
- resnet18_v1 inference graph built in 22.17s!
+ resnet18_v1 inference graph built in 21.89s!
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
index 4d23dff07..093cbf9c0 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -301,7 +301,7 @@ The compilation steps are:
/workspace/python/tvm/relay/build_module.py:431: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 15.30s!
+ yolov3-tiny inference graph built in 15.33s!
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 2497edb08..943a8c1f7 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
@@ -5,7 +5,7 @@
Computation times
=================
-**01:28.883** total execution time for **topic_vta_tutorials_frontend** files:
+**01:28.954** total execution time for **topic_vta_tutorials_frontend** files:
-- **00:46.643**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)
-- **00:42.240**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``)
+- **00:47.111**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)
+- **00:41.844**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``)
diff --git a/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
index a541d4db4..98240040e 100644
--- a/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
@@ -5,7 +5,7 @@
Computation times
=================
-**00:03.526** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.537** total execution time for **topic_vta_tutorials_optimize** files:
-- **00:02.980**: :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)
-- **00:00.546**: :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``)
+- **00:02.986**: :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)
+- **00:00.550**: :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``)
diff --git a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
index e2cf6486e..232627a1d 100644
--- a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
@@ -5,7 +5,7 @@
Computation times
=================
-**00:01.003** total execution time for **topic_vta_tutorials** files:
+**00:01.015** total execution time for **topic_vta_tutorials** files:
-- **00:00.507**: :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``)
-- **00:00.496**: :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``)
+- **00:00.516**: :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``)
+- **00:00.499**: :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``)
diff --git a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
index 4a850f696..458659946 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -306,7 +306,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 92.860 ms
+ Execution time of this operator: 95.797 ms
@@ -402,7 +402,7 @@ resume the status and do more 5 trials.
Resume search:
/usr/local/lib/python3.7/dist-packages/xgboost/training.py:17: UserWarning: Old style callback is deprecated. See: https://xgboost.readthedocs.io/en/latest/python/callbacks.html
warnings.warn(f'Old style callback is deprecated. See: {link}', UserWarning)
-
+ *E
@@ -415,6 +415,11 @@ Expression (TE) language that demonstrates how TVM can optimize computational
operations.
+.. rst-class:: sphx-glr-timing
+
+ **Total running time of the script:** ( 1 minutes 4.129 seconds)
+
+
.. _sphx_glr_download_tutorial_auto_scheduler_matmul_x86.py:
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index a9e5a5b29..e2f83e39f 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -271,7 +271,7 @@ standard deviation.
.. code-block:: none
- {'mean': 495.6507313199995, 'median': 495.76053245000367, 'std': 0.8591542303632894}
+ {'mean': 499.62126257000136, 'median': 499.6272475500007, 'std': 0.5690515703481694}
@@ -485,31 +485,31 @@ 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: 17.21/ 17.21 GFLOPS | Progress: (4/20) | 5.99 s
[Task 1/25] Current/Best: 6.17/ 17.21 GFLOPS | Progress: (8/20) | 8.94 s
[Task 1/25] Current/Best: 11.53/ 22.80 GFLOPS | Progress: (12/20) | 11.44 s
[Task 1/25] Current/Best: 16.87/ 22.80 GFLOPS | Progress: (16/20) | 13.12 s
[Task 1/25] Current/Best: 11.60/ 23.91 GFLOPS | Progress: (20/20) | 14.85 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 11.87/ 13.05 GFLOPS | Progress: (4/20) | 3.72 s
[Task 2/25] Current/Best: 13.95/ 18.11 GFLOPS | Progress: (8/20) | 5.03 s
[Task 2/25] Current/Best: 20.90/ 20.90 GFLOPS | Progress: (12/20) | 6.38 s
[Task 2/25] Current/Best: 12.47/ 20.90 GFLOPS | Progress: (16/20) | 7.65 s
[Task 2/25] Current/Best: 20.19/ 20.90 GFLOPS | Progress: (20/20) | 9.27 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 1.62/ 10.52 GFLOPS | Progress: (4/20) | 5.85 s
[Task 3/25] Current/Best: 15.52/ 16.86 GFLOPS | Progress: (8/20) | 7.77 s
[Task 3/25] Current/Best: 14.85/ 16.86 GFLOPS | Progress: (12/20) | 9.48 s
[Task 3/25] Current/Best: 7.17/ 23.76 GFLOPS | Progress: (16/20) | 11.37 s
[Task 3/25] Current/Best: 12.54/ 23.76 GFLOPS | Progress: (20/20) | 15.93 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.55/ 20.31 GFLOPS | Progress: (4/20) | 2.31 s
[Task 4/25] Current/Best: 6.85/ 20.31 GFLOPS | Progress: (8/20) | 7.00 s
[Task 4/25] Current/Best: 21.78/ 21.78 GFLOPS | Progress: (12/20) | 12.15 s
[Task 4/25] Current/Best: 17.34/ 21.78 GFLOPS | Progress: (16/20) | 14.66 s
[Task 4/25] Current/Best: 12.87/ 21.78 GFLOPS | Progress: (20/20) | 16.87 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.69/ 10.26 GFLOPS | Progress: (4/20) | 2.68 s
[Task 5/25] Current/Best: 11.48/ 12.07 GFLOPS | Progress: (8/20) | 4.96 s
[Task 5/25] Current/Best: 11.44/ 18.09 GFLOPS | Progress: (12/20) | 8.42 s
[Task 5/25] Current/Best: 11.62/ 22.56 GFLOPS | Progress: (16/20) | 9.86 s
[Task 5/25] Current/Best: 11.90/ 22.56 GFLOPS | Progress: (20/20) | 11.78 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.18/ 20.67 GFLOPS | Progress: (4/20) | 4.04 s
[Task 6/25] Current/Best: 18.99/ 20.67 GFLOPS | Progress: (8/20) | 5.79 s
[Task 6/25] Current/Best: 13.28/ 20.67 GFLOPS | Progress: (12/20) | 7.74 s
[Task 6/25] Current/Best: 19.90/ 20.67 GFLOPS | Progress: (16/20) | 9.97 s
[Task 6/25] Current/Best: 3.75/ 20.67 GFLOPS | Progress: (20/20) | 12.52 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.16/ 12.90 GFLOPS | Progress: (4/20) | 3.57 s
[Task 7/25] Current/Best: 20.15/ 21.00 GFLOPS | Progress: (8/20) | 5.08 s
[Task 7/25] Current/Best: 15.30/ 21.00 GFLOPS | Progress: (12/20) | 7.00 s
[Task 7/25] Current/Best: 12.24/ 21.00 GFLOPS | Progress: (16/20) | 9.06 s
[Task 7/25] Current/Best: 6.32/ 21.77 GFLOPS | Progress: (20/20) | 11.50 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 10.17/ 13.67 GFLOPS | Progress: (4/20) | 2.84 s
[Task 8/25] Current/Best: 9.74/ 13.67 GFLOPS | Progress: (8/20) | 8.02 s
[Task 8/25] Current/Best: 12.37/ 13.67 GFLOPS | Progress: (12/20) | 14.51 s
[Task 8/25] Current/Best: 18.88/ 18.88 GFLOPS | Progress: (16/20) | 16.62 s
[Task 8/25] Current/Best: 19.35/ 19.35 GFLOPS | Progress: (20/20) | 23.79 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.33/ 15.66 GFLOPS | Progress: (4/20) | 19.40 s
[Task 9/25] Current/Best: 23.05/ 23.05 GFLOPS | Progress: (8/20) | 21.15 s
[Task 9/25] Current/Best: 8.25/ 23.05 GFLOPS | Progress: (12/20) | 23.72 s
[Task 9/25] Current/Best: 18.01/ 23.05 GFLOPS | Progress: (16/20) | 26.57 s
[Task 9/25] Current/Best: 9.05/ 23.05 GFLOPS | Progress: (20/20) | 35.26 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.29/ 18.29 GFLOPS | Progress: (4/20) | 2.52 s
[Task 10/25] Current/Best: 13.78/ 18.29 GFLOPS | Progress: (8/20) | 4.16 s
[Task 10/25] Current/Best: 12.87/ 18.99 GFLOPS | Progress: (12/20) | 5.70 s
[Task 10/25] Current/Best: 19.12/ 20.36 GFLOPS | Progress: (16/20) | 6.80 s
[Task 10/25] Current/Best: 8.82/ 20.36 GFLOPS | Progress: (20/20
) | 8.36 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.30/ 18.07 GFLOPS | Progress: (4/20) | 3.32 s
[Task 11/25] Current/Best: 16.94/ 18.07 GFLOPS | Progress: (8/20) | 6.13 s
[Task 11/25] Current/Best: 18.05/ 18.07 GFLOPS | Progress: (12/20) | 8.22 s
[Task 11/25] Current/Best: 13.48/ 21.19 GFLOPS | Progress: (16/20) | 11.11 s
[Task 11/25] Current/Best: 19.42/ 21.51 GFLOPS | Progress: (20/20) | 13.21 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.80/ 18.17 GFLOPS | Progress: (4/20) | 5.76 s
[Task 12/25] Current/Best: 5.11/ 18.17 GFLOPS | Progress: (8/20) | 9.67 s
[Task 12/25] Current/Best: 19.01/ 19.01 GFLOPS | Progress: (12/20) | 11.68 s
[Task 12/25] Current/Best: 15.19/ 19.01 GFLOPS | Progress: (16/20) | 14.61 s
[Task 12/25] Current/Best: 15.08/ 19.01 GFLOPS | Progress: (20/20) | 16.52 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.57/ 17.29 GFLOPS | Progress: (4/20) | 3.71 s
[Task 13/25] Current/Best: 16.12/ 20.84 GFLOPS | Progress: (8/20) | 6.33 s
[Task 13/25] Current/Best: 19.50/ 21.49 GFLOPS | Progress: (12/20) | 9.42 s
[Task 13/25] Current/Best: 12.23/ 21.49 GFLOPS | Progress: (16/20) | 12.89 s
[Task 13/25] Current/Best: 18.46/ 21.49 GFLOPS | Progress: (20/20) | 15.23 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.68/ 13.68 GFLOPS | Progress: (4/20) | 3.39 s
[Task 14/25] Current/Best: 6.12/ 13.68 GFLOPS | Progress: (8/20) | 5.60 s
[Task 14/25] Current/Best: 20.46/ 20.46 GFLOPS | Progress: (12/20) | 8.28 s
[Task 14/25] Current/Best: 15.66/ 20.46 GFLOPS | Progress: (16/20) | 10.17 s
[Task 14/25] Current/Best: 17.32/ 20.46 GFLOPS | Progress: (20/20) | 11.98 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.35/ 17.35 GFLOPS | Progress: (4/20) | 6.18 s
[Task 1/25] Current/Best: 6.10/ 17.35 GFLOPS | Progress: (8/20) | 9.09 s
[Task 1/25] Current/Best: 11.48/ 22.64 GFLOPS | Progress: (12/20) | 11.54 s
[Task 1/25] Current/Best: 16.63/ 22.64 GFLOPS | Progress: (16/20) | 13.24 s
[Task 1/25] Current/Best: 11.55/ 23.80 GFLOPS | Progress: (20/20) | 14.98 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.28/ 12.85 GFLOPS | Progress: (4/20) | 3.82 s
[Task 2/25] Current/Best: 14.41/ 18.55 GFLOPS | Progress: (8/20) | 5.15 s
[Task 2/25] Current/Best: 21.13/ 21.13 GFLOPS | Progress: (12/20) | 6.49 s
[Task 2/25] Current/Best: 11.76/ 21.13 GFLOPS | Progress: (16/20) | 7.80 s
[Task 2/25] Current/Best: 20.09/ 21.13 GFLOPS | Progress: (20/20) | 9.39 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 1.63/ 10.55 GFLOPS | Progress: (4/20) | 5.84 s
[Task 3/25] Current/Best: 15.49/ 16.80 GFLOPS | Progress: (8/20) | 7.75 s
[Task 3/25] Current/Best: 14.83/ 16.80 GFLOPS | Progress: (12/20) | 9.48 s
[Task 3/25] Current/Best: 7.18/ 23.69 GFLOPS | Progress: (16/20) | 11.41 s
[Task 3/25] Current/Best: 12.48/ 23.69 GFLOPS | Progress: (20/20) | 15.91 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.56/ 20.32 GFLOPS | Progress: (4/20) | 2.34 s
[Task 4/25] Current/Best: 6.27/ 20.32 GFLOPS | Progress: (8/20) | 6.74 s
[Task 4/25] Current/Best: 21.22/ 21.22 GFLOPS | Progress: (12/20) | 11.34 s
[Task 4/25] Current/Best: 17.10/ 21.22 GFLOPS | Progress: (16/20) | 13.57 s
[Task 4/25] Current/Best: 13.22/ 21.22 GFLOPS | Progress: (20/20) | 15.49 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.50/ 10.12 GFLOPS | Progress: (4/20) | 2.55 s
[Task 5/25] Current/Best: 11.62/ 12.96 GFLOPS | Progress: (8/20) | 4.62 s
[Task 5/25] Current/Best: 10.55/ 17.98 GFLOPS | Progress: (12/20) | 7.75 s
[Task 5/25] Current/Best: 11.66/ 22.60 GFLOPS | Progress: (16/20) | 9.17 s
[Task 5/25] Current/Best: 11.95/ 22.60 GFLOPS | Progress: (20/20) | 11.06 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.21/ 20.75 GFLOPS | Progress: (4/20) | 3.95 s
[Task 6/25] Current/Best: 18.88/ 20.75 GFLOPS | Progress: (8/20) | 5.71 s
[Task 6/25] Current/Best: 13.27/ 20.75 GFLOPS | Progress: (12/20) | 7.64 s
[Task 6/25] Current/Best: 19.95/ 20.75 GFLOPS | Progress: (16/20) | 9.90 s
[Task 6/25] Current/Best: 3.74/ 20.75 GFLOPS | Progress: (20/20) | 12.40 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.18/ 12.14 GFLOPS | Progress: (4/20) | 3.62 s
[Task 7/25] Current/Best: 20.24/ 20.98 GFLOPS | Progress: (8/20) | 5.13 s
[Task 7/25] Current/Best: 14.24/ 20.98 GFLOPS | Progress: (12/20) | 7.09 s
[Task 7/25] Current/Best: 12.23/ 20.98 GFLOPS | Progress: (16/20) | 9.15 s
[Task 7/25] Current/Best: 6.36/ 21.67 GFLOPS | Progress: (20/20) | 11.63 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 10.17/ 14.24 GFLOPS | Progress: (4/20) | 2.86 s
[Task 8/25] Current/Best: 10.27/ 14.24 GFLOPS | Progress: (8/20) | 7.62 s
[Task 8/25] Current/Best: 12.95/ 14.24 GFLOPS | Progress: (12/20) | 13.82 s
[Task 8/25] Current/Best: 19.00/ 19.00 GFLOPS | Progress: (16/20) | 15.90 s
[Task 8/25] Current/Best: 20.00/ 20.00 GFLOPS | Progress: (20/20) | 22.47 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.20/ 14.20 GFLOPS | Progress: (4/20) | 17.97 s
[Task 9/25] Current/Best: 23.21/ 23.21 GFLOPS | Progress: (8/20) | 19.75 s
[Task 9/25] Current/Best: 8.25/ 23.21 GFLOPS | Progress: (12/20) | 22.14 s
[Task 9/25] Current/Best: 17.98/ 23.21 GFLOPS | Progress: (16/20) | 24.74 s
[Task 9/25] Current/Best: 8.97/ 23.21 GFLOPS | Progress: (20/20) | 32.61 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.33/ 18.33 GFLOPS | Progress: (4/20) | 2.54 s
[Task 10/25] Current/Best: 15.49/ 18.33 GFLOPS | Progress: (8/20) | 4.15 s
[Task 10/25] Current/Best: 12.26/ 18.96 GFLOPS | Progress: (12/20) | 5.68 s
[Task 10/25] Current/Best: 19.04/ 20.53 GFLOPS | Progress: (16/20) | 6.79 s
[Task 10/25] Current/Best: 8.94/ 20.53 GFLOPS | Progress: (20/20
) | 8.35 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.25/ 18.04 GFLOPS | Progress: (4/20) | 3.34 s
[Task 11/25] Current/Best: 16.77/ 18.04 GFLOPS | Progress: (8/20) | 6.10 s
[Task 11/25] Current/Best: 18.09/ 18.09 GFLOPS | Progress: (12/20) | 8.16 s
[Task 11/25] Current/Best: 12.85/ 21.00 GFLOPS | Progress: (16/20) | 11.00 s
[Task 11/25] Current/Best: 19.27/ 21.49 GFLOPS | Progress: (20/20) | 13.02 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.66/ 18.29 GFLOPS | Progress: (4/20) | 5.40 s
[Task 12/25] Current/Best: 5.19/ 18.29 GFLOPS | Progress: (8/20) | 9.13 s
[Task 12/25] Current/Best: 19.05/ 19.05 GFLOPS | Progress: (12/20) | 11.09 s
[Task 12/25] Current/Best: 14.51/ 19.05 GFLOPS | Progress: (16/20) | 13.86 s
[Task 12/25] Current/Best: 15.17/ 19.05 GFLOPS | Progress: (20/20) | 15.80 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 7.95/ 17.25 GFLOPS | Progress: (4/20) | 3.66 s
[Task 13/25] Current/Best: 16.05/ 20.79 GFLOPS | Progress: (8/20) | 6.09 s
[Task 13/25] Current/Best: 19.49/ 21.21 GFLOPS | Progress: (12/20) | 9.05 s
[Task 13/25] Current/Best: 12.21/ 21.21 GFLOPS | Progress: (16/20) | 12.50 s
[Task 13/25] Current/Best: 18.70/ 21.21 GFLOPS | Progress: (20/20) | 14.78 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 12.97/ 13.16 GFLOPS | Progress: (4/20) | 3.24 s
[Task 14/25] Current/Best: 6.10/ 13.30 GFLOPS | Progress: (8/20) | 5.41 s
[Task 14/25] Current/Best: 20.49/ 20.49 GFLOPS | Progress: (12/20) | 7.95 s
[Task 14/25] Current/Best: 16.15/ 20.49 GFLOPS | Progress: (16/20) | 9.90 s
[Task 14/25] Current/Best: 17.08/ 20.49 GFLOPS | Progress: (20/20) | 11.70 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
Done.
-
[Task 15/25] Current/Best: 16.13/ 17.64 GFLOPS | Progress: (4/20) | 2.63 s
[Task 15/25] Current/Best: 14.32/ 18.00 GFLOPS | Progress: (8/20) | 4.17 s
[Task 15/25] Current/Best: 10.40/ 22.26 GFLOPS | Progress: (12/20) | 6.43 s
[Task 15/25] Current/Best: 20.31/ 22.26 GFLOPS | Progress: (16/20) | 9.73 s
[Task 15/25] Current/Best: 9.69/ 22.26 GFLOPS | Progress: (20/20) | 10.92 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.65/ 20.65 GFLOPS | Progress: (4/20) | 3.04 s
[Task 16/25] Current/Best: 3.04/ 20.65 GFLOPS | Progress: (8/20) | 4.65 s
[Task 16/25] Current/Best: 19.22/ 20.65 GFLOPS | Progress: (12/20) | 5.86 s
[Task 16/25] Current/Best: 17.51/ 20.65 GFLOPS | Progress: (16/20) | 7.22 s
[Task 16/25] Current/Best: 10.05/ 22.23 GFLOPS | Progress: (20/20) | 9.38 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 13.52/ 18.85 GFLOPS | Progress: (4/20) | 4.69 s
[Task 17/25] Current/Best: 14.36/ 23.27 GFLOPS | Progress: (8/20) | 7.48 s
[Task 17/25] Current/Best: 16.77/ 23.27 GFLOPS | Progress: (12/20) | 9.53 s
[Task 17/25] Current/Best: 16.44/ 23.27 GFLOPS | Progress: (16/20) | 11.73 s
[Task 17/25] Current/Best: 10.02/ 23.27 GFLOPS | Progress: (20/20) | 13.90 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.36/ 18.07 GFLOPS | Progress: (4/20) | 3.75 s
[Task 18/25] Current/Best: 10.60/ 19.03 GFLOPS | Progress: (8/20) | 7.42 s
[Task 18/25] Current/Best: 19.38/ 19.38 GFLOPS | Progress: (12/20) | 9.37 s
[Task 18/25] Current/Best: 9.96/ 19.38 GFLOPS | Progress: (16/20) | 13.26 s
[Task 18/25] Current/Best: 20.43/ 20.43 GFLOPS | Progress: (20/20) | 14.79 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 6.75/ 20.19 GFLOPS | Progress: (4/20) | 6.16 s
[Task 19/25] Current/Best: 2.60/ 20.19 GFLOPS | Progress: (8/20) | 9.51 s
[Task 19/25] Current/Best: 18.40/ 21.55 GFLOPS | Progress: (12/20) | 12.50 s
[Task 19/25] Current/Best: 15.26/ 21.55 GFLOPS | Progress: (16/20) | 15.48 s
[Task 19/25] Current/Best: 2.70/ 23.20 GFLOPS | Progress: (20/20) | 18.27 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 8.59/ 14.93 GFLOPS | Progress: (4/20) | 3.32 s
[Task 20/25] Current/Best: 9.73/ 14.93 GFLOPS | Progress: (8/20) | 6.92 s
[Task 20/25] Current/Best: 2.31/ 16.62 GFLOPS | Progress: (12/20) | 10.78 s Done.
-
[Task 20/25] Current/Best: 12.34/ 16.62 GFLOPS | Progress: (16/20) | 14.69 s
[Task 20/25] Current/Best: 11.75/ 22.05 GFLOPS | Progress: (20/20) | 16.82 s Done.
-
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.40/ 17.62 GFLOPS | Progress: (4/20) | 3.21 s
[Task 21/25] Current/Best: 14.61/ 17.62 GFLOPS | Progress: (8/20) | 4.84 s
[Task 21/25] Current/Best: 1.61/ 17.62 GFLOPS | Progress: (12/20) | 6.95 s
[Task 21/25] Current/Best: 17.59/ 17.62 GFLOPS | Progress: (16/20) | 10.46 s
[Task 21/25] Current/Best: 4.46/ 17.62 GFLOPS | Progress: (20/20) | 17.84 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 16.97 GFLOPS | Progress: (4/20) | 2.60 s
[Task 22/25] Current/Best: 8.73/ 21.75 GFLOPS | Progress: (8/20) | 4.66 s
[Task 22/25] Current/Best: 19.94/ 21.75 GFLOPS | Progress: (12/20) | 7.06 s
[Task 22/25] Current/Best: 14.91/ 21.75 GFLOPS | Progress: (16/20) | 9.17 s
[Task 22/25] Current/Best: 14.43/ 21.75 GFLOPS | Progress: (20/20) |
10.92 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.39/ 20.55 GFLOPS | Progress: (4/20) | 3.19 s
[Task 23/25] Current/Best: 15.18/ 20.55 GFLOPS | Progress: (8/20) | 6.65 s
[Task 23/25] Current/Best: 20.95/ 21.56 GFLOPS | Progress: (12/20) | 8.49 s
[Task 23/25] Current/Best: 5.88/ 21.56 GFLOPS | Progress: (16/20) | 15.68 s
[Task 23/25] Current/Best: 7.73/ 21.56 GFLOPS | Progress: (20/20) | 19.93 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.70/ 8.70 GFLOPS | Progress: (4/20) | 13.89 s
[Task 24/25] Current/Best: 3.44/ 8.70 GFLOPS | Progress: (8/20) | 29.99 s
[Task 24/25] Current/Best: 4.32/ 8.70 GFLOPS | Progress: (12/20) | 54.36 s
[Task 24/25] Current/Best: 6.60/ 8.76 GFLOPS | Progress: (16/20) | 60.10 s Done.
-
[Task 24/25] Current/Best: 3.31/ 8.76 GFLOPS | Progress: (20/20) | 66.45 s Done.
-
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.55/ 2.84 GFLOPS | Progress: (4/20) | 30.28 s
[Task 25/25] Current/Best: 6.01/ 8.15 GFLOPS | Progress: (8/20) | 342.31 s
[Task 25/25] Current/Best: 6.03/ 8.15 GFLOPS | Progress: (12/20) | 371.50 s
[Task 25/25] Current/Best: 5.81/ 8.75 GFLOPS | Progress: (16/20) | 373.35 s
[Task 25/25] Current/Best: 2.88/ 8.79 GFLOPS | Progress: (20/20) | 393.45 s
+
[Task 15/25] Current/Best: 16.09/ 17.61 GFLOPS | Progress: (4/20) | 2.66 s
[Task 15/25] Current/Best: 14.09/ 17.97 GFLOPS | Progress: (8/20) | 4.17 s
[Task 15/25] Current/Best: 10.36/ 22.16 GFLOPS | Progress: (12/20) | 6.36 s
[Task 15/25] Current/Best: 20.32/ 22.16 GFLOPS | Progress: (16/20) | 9.42 s
[Task 15/25] Current/Best: 9.69/ 22.16 GFLOPS | Progress: (20/20) | 10.61 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.57/ 20.57 GFLOPS | Progress: (4/20) | 2.88 s
[Task 16/25] Current/Best: 3.04/ 20.57 GFLOPS | Progress: (8/20) | 4.51 s
[Task 16/25] Current/Best: 19.67/ 20.57 GFLOPS | Progress: (12/20) | 5.72 s
[Task 16/25] Current/Best: 17.62/ 20.57 GFLOPS | Progress: (16/20) | 7.10 s
[Task 16/25] Current/Best: 9.93/ 22.11 GFLOPS | Progress: (20/20) | 9.16 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 13.75/ 18.87 GFLOPS | Progress: (4/20) | 4.70 s
[Task 17/25] Current/Best: 14.37/ 23.03 GFLOPS | Progress: (8/20) | 7.60 s
[Task 17/25] Current/Best: 16.74/ 23.03 GFLOPS | Progress: (12/20) | 9.68 s
[Task 17/25] Current/Best: 16.46/ 23.03 GFLOPS | Progress: (16/20) | 11.80 s
[Task 17/25] Current/Best: 10.02/ 23.03 GFLOPS | Progress: (20/20) | 13.93 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.10/ 18.12 GFLOPS | Progress: (4/20) | 3.64 s
[Task 18/25] Current/Best: 10.59/ 18.12 GFLOPS | Progress: (8/20) | 7.09 s
[Task 18/25] Current/Best: 19.26/ 19.26 GFLOPS | Progress: (12/20) | 9.03 s
[Task 18/25] Current/Best: 9.84/ 19.26 GFLOPS | Progress: (16/20) | 12.60 s
[Task 18/25] Current/Best: 20.65/ 20.65 GFLOPS | Progress: (20/20) | 14.12 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.04/ 20.28 GFLOPS | Progress: (4/20) | 6.11 s
[Task 19/25] Current/Best: 2.61/ 20.28 GFLOPS | Progress: (8/20) | 9.36 s
[Task 19/25] Current/Best: 18.52/ 21.02 GFLOPS | Progress: (12/20) | 12.13 s
[Task 19/25] Current/Best: 15.29/ 21.02 GFLOPS | Progress: (16/20) | 14.95 s
[Task 19/25] Current/Best: 2.70/ 23.10 GFLOPS | Progress: (20/20) | 17.72 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 8.91/ 15.02 GFLOPS | Progress: (4/20) | 3.31 s
[Task 20/25] Current/Best: 10.40/ 15.02 GFLOPS | Progress: (8/20) | 6.81 s
[Task 20/25] Current/Best: 2.32/ 16.61 GFLOPS | Progress: (12/20) | 10.68 s Done.
+
[Task 20/25] Current/Best: 12.43/ 16.61 GFLOPS | Progress: (16/20) | 14.29 s
[Task 20/25] Current/Best: 13.39/ 21.67 GFLOPS | Progress: (20/20) | 16.39 s Done.
+
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.38/ 17.57 GFLOPS | Progress: (4/20) | 3.21 s
[Task 21/25] Current/Best: 14.42/ 17.57 GFLOPS | Progress: (8/20) | 4.78 s
[Task 21/25] Current/Best: 1.61/ 17.57 GFLOPS | Progress: (12/20) | 6.93 s
[Task 21/25] Current/Best: 18.36/ 18.36 GFLOPS | Progress: (16/20) | 10.39 s
[Task 21/25] Current/Best: 4.46/ 18.36 GFLOPS | Progress: (20/20) | 17.66 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 16.94 GFLOPS | Progress: (4/20) | 2.67 s
[Task 22/25] Current/Best: 9.11/ 21.59 GFLOPS | Progress: (8/20) | 4.64 s
[Task 22/25] Current/Best: 19.73/ 21.59 GFLOPS | Progress: (12/20) | 6.96 s
[Task 22/25] Current/Best: 14.95/ 21.59 GFLOPS | Progress: (16/20) | 9.02 s
[Task 22/25] Current/Best: 15.18/ 21.59 GFLOPS | Progress: (20/20) |
10.70 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.40/ 20.20 GFLOPS | Progress: (4/20) | 3.25 s
[Task 23/25] Current/Best: 14.21/ 20.20 GFLOPS | Progress: (8/20) | 6.64 s
[Task 23/25] Current/Best: 20.69/ 21.35 GFLOPS | Progress: (12/20) | 8.47 s
[Task 23/25] Current/Best: 6.20/ 21.35 GFLOPS | Progress: (16/20) | 15.63 s
[Task 23/25] Current/Best: 7.61/ 21.35 GFLOPS | Progress: (20/20) | 19.86 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.56/ 8.56 GFLOPS | Progress: (4/20) | 13.57 s
[Task 24/25] Current/Best: 3.47/ 8.56 GFLOPS | Progress: (8/20) | 29.42 s
[Task 24/25] Current/Best: 4.23/ 8.56 GFLOPS | Progress: (12/20) | 52.81 s
[Task 24/25] Current/Best: 7.00/ 8.86 GFLOPS | Progress: (16/20) | 58.35 s Done.
+
[Task 24/25] Current/Best: 3.20/ 9.01 GFLOPS | Progress: (20/20) | 64.45 s Done.
+
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.55/ 2.86 GFLOPS | Progress: (4/20) | 29.85 s
[Task 25/25] Current/Best: 5.65/ 7.98 GFLOPS | Progress: (8/20) | 342.53 s
[Task 25/25] Current/Best: 5.96/ 7.98 GFLOPS | Progress: (12/20) | 372.22 s
[Task 25/25] Current/Best: 5.79/ 9.19 GFLOPS | Progress: (16/20) | 374.10 s
[Task 25/25] Current/Best: 2.88/ 9.19 GFLOPS | Progress: (20/20) | 394.56 s
The output from this tuning process will look something like this:
@@ -651,8 +651,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 407.4709396300068, 'median': 407.3050235499977, 'std': 0.9091905746638499}
- unoptimized: {'mean': 495.6507313199995, 'median': 495.76053245000367, 'std': 0.8591542303632894}
+ optimized: {'mean': 413.3765781400007, 'median': 413.3688836000033, 'std': 0.4088937171662954}
+ unoptimized: {'mean': 499.62126257000136, 'median': 499.6272475500007, 'std': 0.5690515703481694}
@@ -672,7 +672,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 16 minutes 41.933 seconds)
+ **Total running time of the script:** ( 16 minutes 29.396 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 7d4bb69b5..a01177d45 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -235,7 +235,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.293e-07 secs/op
+ 1.233e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 8f65b0f72..87b87cbff 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -233,7 +233,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0xb3bb240)), stage(b, placeholder(b, 0xd482330)), 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, 0x148a02e0)), stage(b, placeholder(b, 0x2711e310)), 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 1e0133451..efcd7d572 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,17 +5,17 @@
Computation times
=================
-**19:20.725** total execution time for **tutorial** files:
+**19:27.940** total execution time for **tutorial** files:
-- **16:41.933**: :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)
-- **01:03.030**: :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)
-- **00:42.084**: :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``)
-- **00:26.255**: :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)
-- **00:25.111**: :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)
-- **00:01.199**: :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)
-- **00:00.715**: :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)
-- **00:00.218**: :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``)
-- **00:00.049**: :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``)
+- **16:29.396**: :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)
+- **01:04.129**: :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``)
+- **01:02.076**: :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)
+- **00:26.537**: :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)
+- **00:23.585**: :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)
+- **00:01.074**: :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)
+- **00:00.729**: :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)
+- **00:00.224**: :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``)
+- **00:00.051**: :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``)
+- **00:00.048**: :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``)
- **00:00.047**: :ref:`sphx_glr_tutorial_install.py` (``install.py``)
-- **00:00.042**: :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``)
-- **00:00.042**: :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``)
+- **00:00.045**: :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``)
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index dea99c8aa..bbc19b145 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -244,7 +244,7 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
Numpy running time: 0.000008
- naive: 0.000007
+ naive: 0.000006
@@ -335,7 +335,7 @@ compile and run this new schedule with the parallel operation applied:
.. code-block:: none
- parallel: 0.000006
+ parallel: 0.000007
@@ -438,10 +438,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 8.087589999377086e-06 1.0
- naive 6.6765e-06 0.8255240436909179
- parallel 6.271500000000001e-06 0.7754473212023653
- vector 2.4596699999999998e-05 3.0412891852695867
+ numpy 8.157830000072864e-06 1.0
+ naive 5.7963e-06 0.7105198318607067
+ parallel 6.9545e-06 0.8524938617178691
+ vector 2.45903e-05 3.0143187587606466
@@ -830,7 +830,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018239
+ Numpy running time: 0.019525
@@ -886,7 +886,7 @@ optimizations.
.. code-block:: none
- none: 3.560633
+ none: 3.456459
@@ -985,7 +985,7 @@ schedule.
.. code-block:: none
- blocking: 0.311652
+ blocking: 0.326350
@@ -1077,7 +1077,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.342144
+ vectorization: 0.352411
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1149,7 +1149,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.117690
+ loop permutation: 0.116897
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1246,7 +1246,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.109342
+ array packing: 0.108401
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1337,7 +1337,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.110557
+ block caching: 0.108582
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1421,7 +1421,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.144531
+ parallelization: 0.144775
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1500,13 +1500,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.5606331323999996 1.0
- blocking 0.3116520788 0.08752715239436501
- vectorization 0.34214361520000003 0.09609066772048556
- loop permutation 0.11768966029999998 0.03305301499025056
- array packing 0.10934228189999999 0.030708662710864348
- block caching 0.1105574284 0.03104993530335437
- parallelization 0.144530945 0.040591361037687346
+ none 3.4564591374000004 1.0
+ blocking 0.3263503001 0.09441752010570144
+ vectorization 0.35241093230000003 0.10195721062829886
+ loop permutation 0.11689712370000001 0.033819906167885945
+ array packing 0.1084012441 0.03136193421963641
+ block caching 0.10858211960000001 0.03141426392839612
+ parallelization 0.14477499359999998 0.04188534793699366
@@ -1543,7 +1543,7 @@ the computation for specific platforms.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 3.030 seconds)
+ **Total running time of the script:** ( 1 minutes 2.076 seconds)
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/commit_hash b/docs/commit_hash
index 265c02323..7e55b8a67 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-dd986fd989cf002ba7c2665867b4212cbebf26dc
+99caa6533fde8e7264e6659575c03e5ecf54cd6b
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index e532137e0..9049bc9a1 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -401,7 +401,7 @@
</div>
<img alt="../../_images/sphx_glr_from_mxnet_001.png" class="sphx-glr-single-img" src="../../_images/sphx_glr_from_mxnet_001.png" />
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipff051c63-9567-4d89-bd9a-75d341d3c335 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip3182e83b-cf38-41b7-88e3-d2448c562956 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 eb616696f..4e954f961 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -406,42 +406,41 @@ python3 -m pip install -f https://release.oneflow.info <span class="nv">oneflow<
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
0%| | 0.00/41.5M [00:00<?, ?B/s]
- 0%| | 16.0k/41.5M [00:00<07:44, 93.6kB/s]
- 0%| | 48.0k/41.5M [00:00<04:53, 148kB/s]
- 0%| | 96.0k/41.5M [00:00<03:28, 208kB/s]
- 0%| | 160k/41.5M [00:00<02:38, 273kB/s]
- 1%| | 280k/41.5M [00:00<01:41, 427kB/s]
- 1%|1 | 528k/41.5M [00:01<00:55, 772kB/s]
- 2%|2 | 0.98M/41.5M [00:01<00:29, 1.43MB/s]
- 5%|4 | 1.97M/41.5M [00:01<00:14, 2.84MB/s]
- 8%|8 | 3.50M/41.5M [00:01<00:08, 4.81MB/s]
- 12%|#2 | 5.03M/41.5M [00:01<00:06, 6.14MB/s]
- 16%|#5 | 6.56M/41.5M [00:01<00:05, 7.06MB/s]
- 20%|#9 | 8.09M/41.5M [00:02<00:04, 7.69MB/s]
- 23%|##3 | 9.62M/41.5M [00:02<00:04, 8.11MB/s]
- 27%|##6 | 11.1M/41.5M [00:02<00:03, 8.40MB/s]
- 31%|### | 12.7M/41.5M [00:02<00:03, 8.62MB/s]
- 34%|###4 | 14.2M/41.5M [00:02<00:03, 8.77MB/s]
- 38%|###7 | 15.7M/41.5M [00:02<00:03, 8.88MB/s]
- 42%|####1 | 17.3M/41.5M [00:03<00:02, 8.96MB/s]
- 45%|####5 | 18.8M/41.5M [00:03<00:02, 8.99MB/s]
- 49%|####9 | 20.3M/41.5M [00:03<00:02, 9.03MB/s]
- 53%|#####2 | 21.9M/41.5M [00:03<00:02, 9.05MB/s]
- 56%|#####6 | 23.4M/41.5M [00:03<00:02, 9.06MB/s]
- 60%|###### | 24.9M/41.5M [00:04<00:01, 9.08MB/s]
- 64%|######3 | 26.4M/41.5M [00:04<00:01, 9.91MB/s]
- 67%|######7 | 27.9M/41.5M [00:04<00:01, 10.7MB/s]
- 70%|######9 | 28.9M/41.5M [00:04<00:01, 10.3MB/s]
- 72%|#######2 | 29.9M/41.5M [00:04<00:01, 8.88MB/s]
- 75%|#######4 | 31.0M/41.5M [00:04<00:01, 8.13MB/s]
- 78%|#######8 | 32.5M/41.5M [00:04<00:00, 9.73MB/s]
- 81%|######## | 33.6M/41.5M [00:05<00:01, 7.28MB/s]
- 83%|########2 | 34.4M/41.5M [00:05<00:01, 6.61MB/s]
- 86%|########6 | 35.8M/41.5M [00:05<00:00, 7.23MB/s]
- 90%|######### | 37.4M/41.5M [00:05<00:00, 7.80MB/s]
- 94%|#########3| 38.9M/41.5M [00:05<00:00, 8.21MB/s]
- 97%|#########7| 40.4M/41.5M [00:05<00:00, 8.49MB/s]
-100%|##########| 41.5M/41.5M [00:05<00:00, 7.26MB/s]
+ 0%| | 16.0k/41.5M [00:00<08:19, 87.1kB/s]
+ 0%| | 48.0k/41.5M [00:00<05:15, 138kB/s]
+ 0%| | 96.0k/41.5M [00:00<03:44, 194kB/s]
+ 0%| | 160k/41.5M [00:00<02:50, 254kB/s]
+ 1%| | 288k/41.5M [00:00<01:44, 412kB/s]
+ 1%|1 | 552k/41.5M [00:01<00:56, 758kB/s]
+ 3%|2 | 1.05M/41.5M [00:01<00:29, 1.43MB/s]
+ 5%|4 | 2.07M/41.5M [00:01<00:14, 2.78MB/s]
+ 9%|8 | 3.55M/41.5M [00:01<00:08, 4.47MB/s]
+ 12%|#2 | 5.02M/41.5M [00:01<00:06, 5.62MB/s]
+ 16%|#5 | 6.50M/41.5M [00:02<00:05, 6.40MB/s]
+ 19%|#9 | 7.98M/41.5M [00:02<00:05, 6.95MB/s]
+ 23%|##2 | 9.45M/41.5M [00:02<00:04, 7.31MB/s]
+ 26%|##6 | 10.9M/41.5M [00:02<00:04, 7.57MB/s]
+ 30%|##9 | 12.4M/41.5M [00:02<00:03, 7.75MB/s]
+ 33%|###3 | 13.9M/41.5M [00:03<00:03, 7.88MB/s]
+ 37%|###6 | 15.3M/41.5M [00:03<00:03, 7.97MB/s]
+ 41%|#### | 16.8M/41.5M [00:03<00:03, 8.02MB/s]
+ 44%|####4 | 18.3M/41.5M [00:03<00:03, 8.07MB/s]
+ 48%|####7 | 19.8M/41.5M [00:03<00:02, 8.10MB/s]
+ 51%|#####1 | 21.2M/41.5M [00:03<00:02, 8.13MB/s]
+ 55%|#####4 | 22.7M/41.5M [00:04<00:02, 8.14MB/s]
+ 58%|#####8 | 24.2M/41.5M [00:04<00:02, 8.15MB/s]
+ 62%|######1 | 25.7M/41.5M [00:04<00:02, 8.15MB/s]
+ 65%|######5 | 27.1M/41.5M [00:04<00:01, 8.14MB/s]
+ 69%|######8 | 28.6M/41.5M [00:04<00:01, 8.15MB/s]
+ 72%|#######2 | 30.1M/41.5M [00:05<00:01, 8.16MB/s]
+ 76%|#######6 | 31.5M/41.5M [00:05<00:01, 8.17MB/s]
+ 80%|#######9 | 33.0M/41.5M [00:05<00:01, 8.15MB/s]
+ 83%|########3 | 34.5M/41.5M [00:05<00:00, 8.16MB/s]
+ 87%|########6 | 35.9M/41.5M [00:05<00:00, 8.14MB/s]
+ 90%|######### | 37.4M/41.5M [00:06<00:00, 8.14MB/s]
+ 94%|#########3| 38.9M/41.5M [00:06<00:00, 8.16MB/s]
+ 97%|#########7| 40.4M/41.5M [00:06<00:00, 8.16MB/s]
+100%|##########| 41.5M/41.5M [00:06<00:00, 6.72MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_paddle.html b/docs/how_to/compile_models/from_paddle.html
index 5ee7e54b3..34118fddf 100644
--- a/docs/how_to/compile_models/from_paddle.html
+++ b/docs/how_to/compile_models/from_paddle.html
@@ -464,7 +464,7 @@ A quick solution is</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>TVM prediction top-1 id: 282, class name: 282: 'tiger cat',
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.687 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 7.696 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-paddle-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/16269b77359771348d507395692524cf/from_paddle.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_paddle.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_pytorch.html b/docs/how_to/compile_models/from_pytorch.html
index a69b234ef..a07c3a031 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -387,10 +387,9 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 14%|#4 | 6.32M/44.7M [00:00<00:00, 66.3MB/s]
- 28%|##8 | 12.6M/44.7M [00:00<00:00, 62.2MB/s]
- 85%|########5 | 38.0M/44.7M [00:00<00:00, 152MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 139MB/s]
+ 32%|###2 | 14.5M/44.7M [00:00<00:00, 152MB/s]
+ 79%|#######8 | 35.2M/44.7M [00:00<00:00, 190MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 198MB/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 2b3507f17..654b9ac1c 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -607,7 +607,7 @@ 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 0.705 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.671 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-tensorflow-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7f1d3d1b878694c201c614c807cdebc8/from_tensorflow.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_tensorflow.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/sg_execution_times.html b/docs/how_to/compile_models/sg_execution_times.html
index ac236808e..b17bb1263 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -300,18 +300,18 @@
<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>05:29.449</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:41.885</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<ul class="simple">
-<li><p><strong>01:05.687</strong>: <a class="reference internal" href="from_paddle.html#sphx-glr-how-to-compile-models-from-paddle-py"><span class="std std-ref">Compile PaddlePaddle Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_paddle.py</span></code>)</p></li>
-<li><p><strong>01:00.705</strong>: <a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></li>
-<li><p><strong>00:55.510</strong>: <a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></li>
-<li><p><strong>00:39.947</strong>: <a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></li>
-<li><p><strong>00:30.462</strong>: <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></li>
-<li><p><strong>00:21.317</strong>: <a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></li>
-<li><p><strong>00:21.104</strong>: <a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></li>
-<li><p><strong>00:19.561</strong>: <a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></li>
-<li><p><strong>00:12.392</strong>: <a class="reference internal" href="from_keras.html#sphx-glr-how-to-compile-models-from-keras-py"><span class="std std-ref">Compile Keras Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_keras.py</span></code>)</p></li>
-<li><p><strong>00:02.765</strong>: <a class="reference internal" href="from_onnx.html#sphx-glr-how-to-compile-models-from-onnx-py"><span class="std std-ref">Compile ONNX Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_onnx.py</span></code>)</p></li>
+<li><p><strong>01:07.696</strong>: <a class="reference internal" href="from_paddle.html#sphx-glr-how-to-compile-models-from-paddle-py"><span class="std std-ref">Compile PaddlePaddle Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_paddle.py</span></code>)</p></li>
+<li><p><strong>01:05.671</strong>: <a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></li>
+<li><p><strong>00:57.528</strong>: <a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></li>
+<li><p><strong>00:31.436</strong>: <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></li>
+<li><p><strong>00:30.299</strong>: <a class="reference internal" href="from_keras.html#sphx-glr-how-to-compile-models-from-keras-py"><span class="std std-ref">Compile Keras Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_keras.py</span></code>)</p></li>
+<li><p><strong>00:24.564</strong>: <a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></li>
+<li><p><strong>00:21.668</strong>: <a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></li>
+<li><p><strong>00:21.332</strong>: <a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></li>
+<li><p><strong>00:19.288</strong>: <a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></li>
+<li><p><strong>00:02.402</strong>: <a class="reference internal" href="from_onnx.html#sphx-glr-how-to-compile-models-from-onnx-py"><span class="std std-ref">Compile ONNX Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_onnx.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/how_to/deploy_models/deploy_model_on_android.html b/docs/how_to/deploy_models/deploy_model_on_android.html
index 6ed8bbf3e..a87e622ea 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -622,7 +622,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.4971 16.4501 17.2088 16.1058 0.3300
+ 16.5514 16.4103 17.2285 16.2828 0.3394
</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 9650d7eae..db6e642ed 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -409,13 +409,14 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 11%|#1 | 19.4M/170M [00:00<00:00, 202MB/s]
- 27%|##6 | 45.7M/170M [00:00<00:00, 245MB/s]
- 42%|####2 | 71.4M/170M [00:00<00:00, 256MB/s]
- 57%|#####7 | 97.6M/170M [00:00<00:00, 263MB/s]
- 73%|#######2 | 124M/170M [00:00<00:00, 267MB/s]
- 88%|########7 | 149M/170M [00:00<00:00, 256MB/s]
-100%|##########| 170M/170M [00:00<00:00, 257MB/s]
+ 10%|# | 17.5M/170M [00:00<00:00, 184MB/s]
+ 25%|##4 | 42.1M/170M [00:00<00:00, 227MB/s]
+ 39%|###9 | 66.9M/170M [00:00<00:00, 242MB/s]
+ 54%|#####3 | 91.5M/170M [00:00<00:00, 248MB/s]
+ 68%|######8 | 116M/170M [00:00<00:00, 249MB/s]
+ 83%|########3 | 141M/170M [00:00<00:00, 254MB/s]
+ 98%|#########7| 166M/170M [00:00<00:00, 257MB/s]
+100%|##########| 170M/170M [00:00<00:00, 248MB/s]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -508,7 +509,7 @@ 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 5.179 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 12.717 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-object-detection-pytorch-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7795da4b258c8feff986668b95ef57ad/deploy_object_detection_pytorch.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_object_detection_pytorch.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_prequantized.html b/docs/how_to/deploy_models/deploy_prequantized.html
index f2fabafc8..3a7c3a351 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -450,7 +450,7 @@ training. Other models require a full post training calibration.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
0%| | 0.00/13.6M [00:00<?, ?B/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 168MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 173MB/s]
</pre></div>
</div>
</div>
@@ -539,7 +539,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.4557 90.3198 95.9207 90.0651 0.6082
+ 90.4647 90.3588 92.8938 90.2359 0.3188
</pre></div>
</div>
<div class="admonition note">
@@ -578,7 +578,7 @@ 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 6.114 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 7.477 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/fb8217c13f4351224c6cf3aacf1a87fc/deploy_prequantized.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_prequantized.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_prequantized_tflite.html b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
index a70f3da85..5d204c55c 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -540,7 +540,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 118.8269 118.7615 120.3861 118.0224 0.3890
+ 120.2155 120.2355 121.3857 119.3382 0.4114
</pre></div>
</div>
<div class="admonition note">
@@ -568,7 +568,7 @@ network for ARM CPU</span></a>.</p></li>
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 5.735 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 52.626 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-tflite-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/56691c7a27d45da61d112276334640d3/deploy_prequantized_tflite.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_prequantized_tflite.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_quantized.html b/docs/how_to/deploy_models/deploy_quantized.html
index 9ce2dfca1..b5948b519 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -480,7 +480,7 @@ for calibration. But the accuracy might be impacted.</p>
DeprecationWarning,
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 10.407 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 9.417 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-quantized-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7810ecf51bfc05f7d5e8a400ac3e815d/deploy_quantized.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_quantized.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
index 9957690d1..66be0d157 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -415,22 +415,22 @@ 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%|5 | 6952/132723 [00:00<00:01, 69511.95KB/s]
- 12%|#1 | 15504/132723 [00:00<00:01, 78924.83KB/s]
- 18%|#8 | 24054/132723 [00:00<00:01, 81924.50KB/s]
- 25%|##4 | 32546/132723 [00:00<00:01, 83105.03KB/s]
- 31%|### | 41076/132723 [00:00<00:01, 83893.44KB/s]
- 37%|###7 | 49649/132723 [00:00<00:00, 84505.47KB/s]
- 44%|####3 | 58274/132723 [00:00<00:00, 85072.96KB/s]
- 50%|##### | 66902/132723 [00:00<00:00, 85452.86KB/s]
- 57%|#####6 | 75453/132723 [00:00<00:00, 85468.01KB/s]
- 63%|######3 | 84074/132723 [00:01<00:00, 85692.85KB/s]
- 70%|######9 | 92730/132723 [00:01<00:00, 85956.05KB/s]
- 76%|#######6 | 101384/132723 [00:01<00:00, 86127.21KB/s]
- 83%|########2 | 110073/132723 [00:01<00:00, 86353.67KB/s]
- 89%|########9 | 118709/132723 [00:01<00:00, 86059.40KB/s]
- 96%|#########5| 127386/132723 [00:01<00:00, 86269.44KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 84823.44KB/s]
+ 5%|5 | 6933/132723 [00:00<00:01, 69323.29KB/s]
+ 12%|#1 | 15330/132723 [00:00<00:01, 77935.42KB/s]
+ 18%|#7 | 23716/132723 [00:00<00:01, 80633.78KB/s]
+ 24%|##4 | 32107/132723 [00:00<00:01, 81923.65KB/s]
+ 30%|### | 40469/132723 [00:00<00:01, 82531.73KB/s]
+ 37%|###6 | 48818/132723 [00:00<00:01, 82848.61KB/s]
+ 43%|####3 | 57205/132723 [00:00<00:00, 83179.98KB/s]
+ 49%|####9 | 65620/132723 [00:00<00:00, 83487.52KB/s]
+ 56%|#####5 | 73976/132723 [00:00<00:00, 83507.40KB/s]
+ 62%|######2 | 82334/132723 [00:01<00:00, 83527.99KB/s]
+ 68%|######8 | 90694/132723 [00:01<00:00, 83547.13KB/s]
+ 75%|#######4 | 99111/132723 [00:01<00:00, 83734.98KB/s]
+ 81%|########1 | 107612/132723 [00:01<00:00, 84118.68KB/s]
+ 87%|########7 | 116061/132723 [00:01<00:00, 84227.88KB/s]
+ 94%|#########3| 124484/132723 [00:01<00:00, 84218.50KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 82982.41KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -470,7 +470,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
</pre></div>
</div>
<img alt="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" class="sphx-glr-single-img" src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" />
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 24.549 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 29.528 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-ssd-gluoncv-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/cccb17d28e5e8b2e94ea8cd5ec59f6ed/deploy_ssd_gluoncv.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_ssd_gluoncv.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/sg_execution_times.html b/docs/how_to/deploy_models/sg_execution_times.html
index 1c6cf4e66..0527af4a8 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -300,16 +300,16 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>10:42.921</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>10:43.510</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<ul class="simple">
-<li><p><strong>03:05.179</strong>: <a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></li>
-<li><p><strong>02:24.549</strong>: <a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></li>
-<li><p><strong>02:05.735</strong>: <a class="reference internal" href="deploy_prequantized_tflite.html#sphx-glr-how-to-deploy-models-deploy-prequantized-tflite-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite)</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized_tflite.py</span></code>)</p></li>
-<li><p><strong>01:10.407</strong>: <a class="reference internal" href="deploy_quantized.html#sphx-glr-how-to-deploy-models-deploy-quantized-py"><span class="std std-ref">Deploy a Quantized Model on Cuda</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_quantized.py</span></code>)</p></li>
-<li><p><strong>01:06.114</strong>: <a class="reference internal" href="deploy_prequantized.html#sphx-glr-how-to-deploy-models-deploy-prequantized-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized.py</span></code>)</p></li>
-<li><p><strong>00:28.313</strong>: <a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></li>
-<li><p><strong>00:22.421</strong>: <a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></li>
-<li><p><strong>00:00.204</strong>: <a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></li>
+<li><p><strong>03:12.717</strong>: <a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></li>
+<li><p><strong>02:29.528</strong>: <a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></li>
+<li><p><strong>01:52.626</strong>: <a class="reference internal" href="deploy_prequantized_tflite.html#sphx-glr-how-to-deploy-models-deploy-prequantized-tflite-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite)</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized_tflite.py</span></code>)</p></li>
+<li><p><strong>01:09.417</strong>: <a class="reference internal" href="deploy_quantized.html#sphx-glr-how-to-deploy-models-deploy-quantized-py"><span class="std std-ref">Deploy a Quantized Model on Cuda</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_quantized.py</span></code>)</p></li>
+<li><p><strong>01:07.477</strong>: <a class="reference internal" href="deploy_prequantized.html#sphx-glr-how-to-deploy-models-deploy-prequantized-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized.py</span></code>)</p></li>
+<li><p><strong>00:29.206</strong>: <a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></li>
+<li><p><strong>00:22.330</strong>: <a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></li>
+<li><p><strong>00:00.208</strong>: <a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index ce5ca3a9a..57fcbb4b0 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -588,7 +588,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip8f6aad35-5e5a-4926-b67d-3d9f994e37ee 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.zipefde4ed6-646f-48db-be3b-a007f0e06a16 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 763a75d66..4bf4abd0d 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -300,12 +300,12 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:38.617</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:38.629</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:35.023</strong>: <a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></li>
-<li><p><strong>00:02.320</strong>: <a class="reference internal" href="use_pass_instrument.html#sphx-glr-how-to-extend-tvm-use-pass-instrument-py"><span class="std std-ref">How to Use TVM Pass Instrument</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_instrument.py</span></code>)</p></li>
-<li><p><strong>00:01.067</strong>: <a class="reference internal" href="use_pass_infra.html#sphx-glr-how-to-extend-tvm-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></li>
-<li><p><strong>00:00.208</strong>: <a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></li>
+<li><p><strong>00:35.062</strong>: <a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></li>
+<li><p><strong>00:02.305</strong>: <a class="reference internal" href="use_pass_instrument.html#sphx-glr-how-to-extend-tvm-use-pass-instrument-py"><span class="std std-ref">How to Use TVM Pass Instrument</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_instrument.py</span></code>)</p></li>
+<li><p><strong>00:01.053</strong>: <a class="reference internal" href="use_pass_infra.html#sphx-glr-how-to-extend-tvm-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></li>
+<li><p><strong>00:00.210</strong>: <a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 2e050bb33..d2be8ab70 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -486,10 +486,10 @@ profile the execution time of each passes.</p>
</div>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 5976us [5976us] (45.48%; 45.48%)
-FoldScaleAxis: 7162us [2us] (54.52%; 54.52%)
- FoldConstant: 7160us [1460us] (54.50%; 99.97%)
- InferType: 5700us [5700us] (43.39%; 79.61%)
+InferType: 6080us [6080us] (45.78%; 45.78%)
+FoldScaleAxis: 7201us [2us] (54.22%; 54.22%)
+ FoldConstant: 7199us [1477us] (54.21%; 99.97%)
+ InferType: 5722us [5722us] (43.09%; 79.49%)
</pre></div>
</div>
</div>
@@ -512,10 +512,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
</div>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 5761us [5761us] (44.48%; 44.48%)
-FoldScaleAxis: 7192us [2us] (55.52%; 55.52%)
- FoldConstant: 7190us [1518us] (55.51%; 99.97%)
- InferType: 5672us [5672us] (43.79%; 78.89%)
+InferType: 5825us [5825us] (44.91%; 44.91%)
+FoldScaleAxis: 7146us [2us] (55.09%; 55.09%)
+ FoldConstant: 7144us [1502us] (55.08%; 99.97%)
+ InferType: 5642us [5642us] (43.50%; 78.98%)
</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 8f7dbcbf7..510fc2ec5 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -534,7 +534,7 @@ latency of convolution.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 46.673771 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.145100 ms
</pre></div>
</div>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-optimize-operators-opt-conv-cuda-py">
diff --git a/docs/how_to/optimize_operators/opt_conv_tensorcore.html b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
index ef22b1af0..ccd0057c9 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -878,7 +878,7 @@ be able to run on our build server</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 6.921626 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 6.861769 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 e0bded8a5..5abf0b0fa 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -431,8 +431,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018830
-Baseline: 3.399444
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019530
+Baseline: 3.450291
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -494,7 +494,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.308552
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.313789
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -563,7 +563,7 @@ vastly.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.341195
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.346624
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -626,7 +626,7 @@ the access pattern for A matrix is more cache friendly.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.125715
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.118491
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -711,7 +711,7 @@ flattening.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.112148
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.111130
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -799,7 +799,7 @@ write to C when all the block results are ready.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111770
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111483
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -891,7 +891,7 @@ write to C when all the block results are ready.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.145485
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.145561
</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 3fd367be3..feedb12a0 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -300,11 +300,11 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:35.347</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:35.742</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:32.707</strong>: <a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></li>
-<li><p><strong>00:01.403</strong>: <a class="reference internal" href="opt_conv_tensorcore.html#sphx-glr-how-to-optimize-operators-opt-conv-tensorcore-py"><span class="std std-ref">How to optimize convolution using TensorCores</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_tensorcore.py</span></code>)</p></li>
-<li><p><strong>00:01.236</strong>: <a class="reference internal" href="opt_conv_cuda.html#sphx-glr-how-to-optimize-operators-opt-conv-cuda-py"><span class="std std-ref">How to optimize convolution on GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_cuda.py</span></code>)</p></li>
+<li><p><strong>00:32.981</strong>: <a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></li>
+<li><p><strong>00:01.478</strong>: <a class="reference internal" href="opt_conv_tensorcore.html#sphx-glr-how-to-optimize-operators-opt-conv-tensorcore-py"><span class="std std-ref">How to optimize convolution using TensorCores</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_tensorcore.py</span></code>)</p></li>
+<li><p><strong>00:01.283</strong>: <a class="reference internal" href="opt_conv_cuda.html#sphx-glr-how-to-optimize-operators-opt-conv-cuda-py"><span class="std std-ref">How to optimize convolution on GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_cuda.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
index 290db26ff..fe24d5cb4 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -300,14 +300,14 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:04.761</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>05:02.478</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<ul class="simple">
-<li><p><strong>02:27.817</strong>: <a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></li>
-<li><p><strong>01:19.903</strong>: <a class="reference internal" href="tune_network_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-x86-py"><span class="std std-ref">Auto-scheduling a Neural Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_x86.py</span></code>)</p></li>
-<li><p><strong>00:40.543</strong>: <a class="reference internal" href="tune_network_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></li>
-<li><p><strong>00:18.839</strong>: <a class="reference internal" href="tune_sparse_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-sparse-x86-py"><span class="std std-ref">Auto-scheduling Sparse Matrix Multiplication on CPU with Custom Sketch Rule</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_sparse_x86.py</span></code>)</p></li>
-<li><p><strong>00:09.046</strong>: <a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></li>
-<li><p><strong>00:08.613</strong>: <a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></li>
+<li><p><strong>02:25.793</strong>: <a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></li>
+<li><p><strong>01:20.595</strong>: <a class="reference internal" href="tune_network_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-x86-py"><span class="std std-ref">Auto-scheduling a Neural Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_x86.py</span></code>)</p></li>
+<li><p><strong>00:41.396</strong>: <a class="reference internal" href="tune_network_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></li>
+<li><p><strong>00:16.701</strong>: <a class="reference internal" href="tune_sparse_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-sparse-x86-py"><span class="std std-ref">Auto-scheduling Sparse Matrix Multiplication on CPU with Custom Sketch Rule</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_sparse_x86.py</span></code>)</p></li>
+<li><p><strong>00:09.128</strong>: <a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></li>
+<li><p><strong>00:08.864</strong>: <a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html b/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
index 02cb55225..8920aad7b 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
@@ -470,11 +470,11 @@ cooperative fetching, unrolling and operator fusion.</p>
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 8;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 56;
allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [648]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [4608]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224 {
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [288]), 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" = 32 {
conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
@@ -489,124 +489,1103 @@ cooperative fetching, unrolling and operator fusion.</p>
conv2d_nchw_1[11] = 0f32
conv2d_nchw_1[12] = 0f32
conv2d_nchw_1[13] = 0f32
- for (rc.outer.outer: int32, 0, 64) {
- let cse_var_2: int32 = (rc.outer.outer*392)
- let cse_var_1: int32 = (rc.outer.outer*72)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [648], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((9 <= floormod(threadIdx.x_1, 81)) && (floormod(threadIdx.x_1, 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv(threadIdx.x_1, 81)*49)) + (floordiv(floormod(threadIdx.x_1, 81), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 224), 81)) && (floormod((threadIdx.x_1 + 62), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 224), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- if @tir.likely((threadIdx.x_1 < 200), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 448), 81)) && (floormod((threadIdx.x_1 + 43), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 448), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 448), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 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, [4608], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 72)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((blockIdx.x*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 28), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((blockIdx.x*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 56), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[((((blockIdx.x*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 84), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((blockIdx.x*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 112), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((blockIdx.x*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 140), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[((((blockIdx.x*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 168), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[((((blockIdx.x*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 196), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((blockIdx.x*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 224), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel[(((((blockIdx.x*294912) + (floordiv(floordiv(threadIdx.x_2, 8), 9)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72)) + 129024)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((blockIdx.x*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 280), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel[((((blockIdx.x*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 308), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[((((blockIdx.x*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 336), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel[((((blockIdx.x*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 364), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel[((((blockIdx.x*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 392), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 3360)] = kernel[((((blockIdx.x*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 420), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 3584)] = kernel[((((blockIdx.x*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 448), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 3808)] = kernel[((((blockIdx.x*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 476), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 4032)] = kernel[(((((blockIdx.x*294912) + (floordiv(floordiv(threadIdx.x_2, 8), 9)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72)) + 258048)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 4256)] = kernel[((((blockIdx.x*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 532), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- if @tir.likely((threadIdx.x_2 < 128), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 4480)] = kernel[((((blockIdx.x*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 560), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
- }
- for (rc.outer.inner: int32, 0, 4) {
- for (rx.outer.inner: int32, 0, 3) {
- for (ff.outer.inner: int32, 0, 2) {
- let cse_var_9: int32 = (ff.outer.inner*7)
- let cse_var_8: int32 = (cse_var_9 + 6)
- let cse_var_7: int32 = (cse_var_9 + 5)
- let cse_var_6: int32 = (cse_var_9 + 4)
- let cse_var_5: int32 = (cse_var_9 + 3)
- let cse_var_4: int32 = (cse_var_9 + 2)
- let cse_var_3: int32 = (cse_var_9 + 1)
- {
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[(((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 3)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 6)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 12)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 15)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 3)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 6)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 12)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 15)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 3)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 6)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 12)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 15)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 3)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 6)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 12)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 15)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 3)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 6)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 12)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 15)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 3)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 6)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 12)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 144)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 15)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 3)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 72)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 6)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 144)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 12)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((rc.outer.inner*162) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 153)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + rx.outer.inner) + 15)]))
- }
+ for (rc.outer.outer: int32, 0, 16) {
+ for (ry.outer.outer: int32, 0, 3) {
+ let cse_var_3: int32 = (rc.outer.outer*1568)
+ let cse_var_2: int32 = (ry.outer.outer*7)
+ let cse_var_1: int32 = (ry.outer.outer*3)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [288], [], scope="shared")[threadIdx.x_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, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[(((((cse_var_3 + (floordiv(threadIdx.x_1, 9)*49)) + cse_var_2) + (floormod(blockIdx.x, 7)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32 [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 32)] = @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 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[(((((cse_var_3 + (floordiv((threadIdx.x_1 + 32), 9)*49)) + cse_var_2) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 64)] = @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 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[(((((cse_var_3 + (floordiv((threadIdx.x_1 + 64), 9)*49)) + cse_var_2) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 96)] = @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 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[(((((cse_var_3 + (floordiv((threadIdx.x_1 + 96), 9)*49)) + cse_var_2) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 128)] = @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 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[(((((cse_var_3 + (floordiv((threadIdx.x_1 + 128), 9)*49)) + cse_var_2) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 160)] = @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 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[(((((cse_var_3 + (floordiv((threadIdx.x_1 + 160), 9)*49)) + cse_var_2) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 192)] = @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 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[(((((cse_var_3 + (floordiv((threadIdx.x_1 + 192), 9)*49)) + cse_var_2) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 224)] = @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 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[(((((cse_var_3 + (floordiv((threadIdx.x_1 + 224), 9)*49)) + cse_var_2) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 256)] = @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[(((((cse_var_3 + (floordiv((threadIdx.x_1 + 256), 9)*49)) + cse_var_2) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1: Buffer(kernel.shared, float32, [6144], [], scope="shared")[threadIdx.x_2] = kernel[(((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 32)] = kernel[(((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[(((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 96)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 4608)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 4608)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 160)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 4608)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 9216)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 9216)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 9216)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 288)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 13824)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 13824)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 352)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 13824)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 18432)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 416)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 18432)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 18432)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 480)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 23040)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 23040)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 544)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 23040)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 27648)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 608)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 27648)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 27648)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 32256)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 32256)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 736)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 32256)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 800)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 864)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 41472)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 41472)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 928)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 41472)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 46080)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 992)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 46080)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 46080)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1056)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 50688)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 50688)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 50688)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 55296)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1184)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 55296)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 55296)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1248)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 59904)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 59904)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1312)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 59904)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 64512)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1376)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 64512)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 64512)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1440)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 69120)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 69120)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1504)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 69120)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1632)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 78336)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 78336)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1696)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 78336)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 82944)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1760)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 82944)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 82944)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1824)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 87552)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 87552)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1888)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 87552)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 92160)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1952)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 92160)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 92160)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 96768)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 96768)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2080)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 96768)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 101376)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2144)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 101376)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 101376)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2208)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 105984)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 105984)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2272)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 105984)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2336)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2400)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 115200)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 115200)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 115200)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 119808)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2528)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 119808)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 119808)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2592)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 124416)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 124416)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2656)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 124416)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 129024)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2720)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 129024)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 129024)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2784)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 133632)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 133632)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2848)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 133632)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 138240)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 138240)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 138240)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2976)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 142848)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 142848)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3040)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 142848)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3072)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 147456)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3104)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 147456)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 147456)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3168)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 152064)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3200)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 152064)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3232)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 152064)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3264)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 156672)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3296)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 156672)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3328)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 156672)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3360)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 161280)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3392)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 161280)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3424)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 161280)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3456)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 165888)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3488)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 165888)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3520)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 165888)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3552)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 170496)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3584)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 170496)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3616)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 170496)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3648)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 175104)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3680)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 175104)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3712)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 175104)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3744)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 179712)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3776)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 179712)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3808)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 179712)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3840)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 184320)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3872)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 184320)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3904)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 184320)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3936)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 188928)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3968)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 188928)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4000)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 188928)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4032)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 193536)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4064)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 193536)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4096)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 193536)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4128)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 198144)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4160)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 198144)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4192)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 198144)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4224)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 202752)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4256)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 202752)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4288)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 202752)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4320)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 207360)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4352)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 207360)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4384)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 207360)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4416)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 211968)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4448)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 211968)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4480)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 211968)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4512)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 216576)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4544)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 216576)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4576)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 216576)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4608)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 221184)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4640)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 221184)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4672)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 221184)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4704)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 225792)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4736)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 225792)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4768)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 225792)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4800)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 230400)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4832)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 230400)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4864)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 230400)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4896)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 235008)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4928)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 235008)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4960)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 235008)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4992)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 239616)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5024)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 239616)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5056)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 239616)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5088)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 244224)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5120)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 244224)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5152)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 244224)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5184)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 248832)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5216)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 248832)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5248)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 248832)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5280)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 253440)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5312)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 253440)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5344)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 253440)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5376)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5408)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 258048)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5440)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 258048)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5472)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 262656)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5504)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 262656)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5536)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 262656)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5568)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 267264)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5600)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 267264)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5632)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 267264)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5664)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 271872)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5696)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 271872)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5728)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 271872)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5760)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 276480)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5792)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 276480)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5824)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 276480)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5856)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 281088)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5888)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 281088)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5920)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 281088)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5952)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 285696)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 5984)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 285696)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 6016)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 285696)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 6048)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 290304)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 6080)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 290304)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 6112)] = kernel[((((((floordiv(blockIdx.x, 7)*294912) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 290304)]
+ for (ff.outer.inner: int32, 0, 2) {
+ let cse_var_10: int32 = (ff.outer.inner*7)
+ let cse_var_9: int32 = (cse_var_10 + 6)
+ let cse_var_8: int32 = (cse_var_10 + 5)
+ let cse_var_7: int32 = (cse_var_10 + 4)
+ let cse_var_6: int32 = (cse_var_10 + 3)
+ let cse_var_5: int32 = (cse_var_10 + 2)
+ let cse_var_4: int32 = (cse_var_10 + 1)
+ {
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*192) + (ff.outer.inner*96))]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*192) + (ff.outer.inner*96))]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*192) + (ff.outer.inner*96))]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*192) + (ff.outer.inner*96))]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*192) + (ff.outer.inner*96))]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*192) + (ff.outer.inner*96))]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*192) + (ff.outer.inner*96))]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[1]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 1)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[2]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 1)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[3]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 1)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[4]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 1)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[5]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 1)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[6]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 1)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[7]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 1)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[2]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 2)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[3]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 2)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[4]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 2)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[5]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 2)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[6]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 2)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[7]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 2)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[8]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 2)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[9]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 3)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[10]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 3)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[11]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 3)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[12]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 3)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[13]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 3)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[14]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 3)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[15]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 3)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[10]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 4)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[11]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 4)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[12]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 4)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[13]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 4)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[14]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 4)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[15]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 4)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[16]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 4)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[11]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 5)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[12]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 5)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[13]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 5)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[14]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 5)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[15]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 5)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[16]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 5)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[17]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 5)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[18]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 6)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[19]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 6)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[20]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 6)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[21]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 6)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[22]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 6)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[23]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 6)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[24]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 6)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[19]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 7)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[20]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 7)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[21]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 7)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[22]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 7)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[23]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 7)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[24]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 7)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[25]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 7)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[20]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 8)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[21]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 8)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[22]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 8)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[23]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 8)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[24]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 8)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[25]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 8)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[26]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 8)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[27]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 9)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[28]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 9)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[29]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 9)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[30]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 9)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[31]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 9)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[32]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 9)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[33]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 9)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[28]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 10)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[29]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 10)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[30]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 10)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[31]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 10)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[32]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 10)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[33]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 10)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[34]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 10)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[29]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 11)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[30]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 11)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[31]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 11)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[32]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 11)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[33]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 11)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[34]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 11)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[35]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 11)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[36]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 12)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[37]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 12)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[38]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 12)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[39]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 12)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[40]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 12)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[41]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 12)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[42]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 12)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[37]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 13)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[38]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 13)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[39]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 13)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[40]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 13)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[41]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 13)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[42]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 13)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[43]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 13)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[38]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 14)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[39]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 14)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[40]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 14)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[41]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 14)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[42]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 14)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[43]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 14)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[44]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 14)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[45]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 15)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[46]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 15)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[47]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 15)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[48]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 15)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[49]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 15)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[50]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 15)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[51]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 15)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[46]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 16)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[47]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 16)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[48]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 16)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[49]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 16)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[50]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 16)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[51]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 16)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[52]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 16)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[47]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 17)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[48]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 17)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[49]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 17)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[50]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 17)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[51]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 17)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[52]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 17)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[53]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 17)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[54]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 18)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[55]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 18)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[56]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 18)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[57]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 18)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[58]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 18)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[59]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 18)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[60]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 18)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[55]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 19)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[56]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 19)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[57]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 19)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[58]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 19)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[59]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 19)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[60]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 19)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[61]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 19)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[56]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 20)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[57]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 20)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[58]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 20)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[59]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 20)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[60]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 20)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[61]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 20)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[62]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 20)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[63]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 21)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[64]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 21)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[65]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 21)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[66]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 21)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[67]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 21)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[68]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 21)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[69]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 21)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[64]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 22)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[65]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 22)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[66]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 22)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[67]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 22)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[68]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 22)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[69]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 22)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[70]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 22)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[65]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 23)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[66]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 23)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[67]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 23)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[68]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 23)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[69]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 23)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[70]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 23)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[71]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 23)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[72]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 24)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[73]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 24)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[74]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 24)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[75]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 24)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[76]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 24)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[77]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 24)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[78]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 24)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[73]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 25)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[74]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 25)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[75]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 25)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[76]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 25)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[77]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 25)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[78]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 25)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[79]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 25)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[74]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 26)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[75]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 26)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[76]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 26)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[77]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 26)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[78]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 26)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[79]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 26)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[80]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 26)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[81]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 27)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[82]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 27)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[83]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 27)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[84]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 27)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[85]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 27)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[86]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 27)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[87]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 27)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[82]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 28)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[83]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 28)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[84]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 28)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[85]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 28)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[86]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 28)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[87]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 28)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[88]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 28)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[83]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 29)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[84]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 29)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[85]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 29)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[86]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 29)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[87]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 29)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[88]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 29)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[89]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 29)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[90]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 30)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[91]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 30)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[92]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 30)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[93]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 30)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[94]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 30)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[95]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 30)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[96]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 30)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[91]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 31)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[92]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 31)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[93]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 31)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[94]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 31)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[95]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 31)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[96]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 31)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[97]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 31)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[92]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 32)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[93]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 32)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[94]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 32)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[95]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 32)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[96]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 32)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[97]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 32)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[98]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 32)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[99]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 33)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[100]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 33)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[101]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 33)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[102]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 33)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[103]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 33)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[104]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 33)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[105]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 33)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[100]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 34)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[101]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 34)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[102]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 34)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[103]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 34)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[104]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 34)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[105]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 34)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[106]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 34)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[101]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 35)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[102]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 35)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[103]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 35)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[104]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 35)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[105]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 35)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[106]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 35)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[107]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 35)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[108]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 36)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[109]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 36)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[110]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 36)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[111]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 36)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[112]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 36)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[113]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 36)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[114]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 36)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[109]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 37)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[110]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 37)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[111]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 37)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[112]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 37)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[113]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 37)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[114]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 37)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[115]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 37)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[110]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 38)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[111]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 38)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[112]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 38)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[113]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 38)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[114]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 38)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[115]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 38)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[116]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 38)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[117]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 39)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[118]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 39)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[119]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 39)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[120]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 39)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[121]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 39)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[122]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 39)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[123]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 39)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[118]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 40)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[119]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 40)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[120]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 40)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[121]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 40)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[122]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 40)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[123]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 40)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[124]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 40)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[119]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 41)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[120]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 41)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[121]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 41)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[122]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 41)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[123]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 41)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[124]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 41)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[125]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 41)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[126]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 42)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[127]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 42)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[128]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 42)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[129]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 42)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[130]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 42)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[131]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 42)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[132]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 42)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[127]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 43)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[128]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 43)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[129]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 43)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[130]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 43)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[131]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 43)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[132]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 43)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[133]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 43)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[128]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 44)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[129]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 44)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[130]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 44)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[131]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 44)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[132]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 44)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[133]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 44)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[134]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 44)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[135]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 45)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[136]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 45)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[137]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 45)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[138]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 45)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[139]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 45)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[140]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 45)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[141]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 45)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[136]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 46)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[137]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 46)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[138]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 46)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[139]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 46)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[140]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 46)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[141]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 46)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[142]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 46)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[137]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 47)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[138]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 47)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[139]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 47)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[140]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 47)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[141]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 47)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[142]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 47)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[143]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 47)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[144]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 48)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[145]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 48)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[146]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 48)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[147]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 48)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[148]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 48)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[149]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 48)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[150]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 48)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[145]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 49)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[146]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 49)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[147]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 49)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[148]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 49)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[149]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 49)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[150]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 49)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[151]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 49)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[146]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 50)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[147]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 50)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[148]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 50)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[149]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 50)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[150]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 50)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[151]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 50)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[152]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 50)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[153]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 51)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[154]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 51)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[155]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 51)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[156]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 51)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[157]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 51)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[158]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 51)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[159]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 51)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[154]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 52)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[155]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 52)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[156]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 52)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[157]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 52)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[158]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 52)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[159]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 52)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[160]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 52)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[155]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 53)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[156]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 53)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[157]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 53)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[158]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 53)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[159]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 53)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[160]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 53)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[161]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 53)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[162]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 54)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[163]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 54)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[164]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 54)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[165]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 54)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[166]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 54)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[167]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 54)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[168]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 54)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[163]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 55)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[164]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 55)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[165]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 55)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[166]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 55)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[167]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 55)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[168]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 55)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[169]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 55)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[164]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 56)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[165]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 56)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[166]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 56)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[167]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 56)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[168]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 56)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[169]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 56)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[170]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 56)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[171]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 57)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[172]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 57)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[173]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 57)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[174]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 57)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[175]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 57)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[176]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 57)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[177]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 57)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[172]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 58)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[173]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 58)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[174]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 58)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[175]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 58)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[176]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 58)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[177]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 58)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[178]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 58)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[173]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 59)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[174]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 59)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[175]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 59)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[176]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 59)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[177]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 59)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[178]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 59)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[179]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 59)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[180]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 60)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[181]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 60)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[182]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 60)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[183]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 60)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[184]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 60)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[185]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 60)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[186]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 60)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[181]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 61)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[182]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 61)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[183]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 61)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[184]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 61)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[185]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 61)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[186]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 61)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[187]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 61)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[182]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 62)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[183]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 62)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[184]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 62)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[185]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 62)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[186]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 62)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[187]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 62)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[188]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 62)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[189]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 63)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[190]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 63)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[191]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 63)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[192]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 63)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[193]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 63)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[194]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 63)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[195]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 63)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[190]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 64)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[191]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 64)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[192]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 64)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[193]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 64)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[194]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 64)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[195]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 64)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[196]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 64)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[191]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 65)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[192]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 65)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[193]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 65)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[194]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 65)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[195]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 65)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[196]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 65)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[197]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 65)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[198]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 66)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[199]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 66)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[200]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 66)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[201]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 66)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[202]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 66)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[203]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 66)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[204]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 66)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[199]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 67)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[200]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 67)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[201]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 67)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[202]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 67)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[203]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 67)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[204]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 67)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[205]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 67)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[200]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 68)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[201]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 68)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[202]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 68)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[203]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 68)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[204]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 68)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[205]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 68)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[206]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 68)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[207]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 69)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[208]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 69)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[209]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 69)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[210]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 69)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[211]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 69)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[212]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 69)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[213]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 69)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[208]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 70)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[209]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 70)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[210]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 70)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[211]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 70)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[212]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 70)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[213]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 70)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[214]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 70)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[209]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 71)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[210]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 71)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[211]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 71)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[212]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 71)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[213]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 71)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[214]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 71)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[215]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 71)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[216]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 72)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[217]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 72)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[218]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 72)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[219]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 72)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[220]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 72)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[221]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 72)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[222]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 72)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[217]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 73)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[218]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 73)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[219]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 73)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[220]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 73)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[221]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 73)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[222]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 73)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[223]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 73)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[218]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 74)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[219]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 74)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[220]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 74)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[221]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 74)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[222]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 74)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[223]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 74)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[224]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 74)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[225]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 75)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[226]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 75)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[227]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 75)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[228]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 75)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[229]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 75)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[230]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 75)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[231]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 75)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[226]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 76)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[227]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 76)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[228]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 76)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[229]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 76)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[230]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 76)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[231]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 76)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[232]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 76)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[227]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 77)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[228]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 77)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[229]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 77)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[230]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 77)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[231]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 77)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[232]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 77)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[233]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 77)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[234]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 78)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[235]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 78)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[236]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 78)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[237]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 78)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[238]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 78)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[239]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 78)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[240]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 78)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[235]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 79)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[236]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 79)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[237]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 79)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[238]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 79)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[239]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 79)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[240]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 79)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[241]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 79)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[236]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 80)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[237]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 80)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[238]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 80)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[239]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 80)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[240]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 80)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[241]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 80)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[242]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 80)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[243]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 81)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[244]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 81)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[245]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 81)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[246]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 81)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[247]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 81)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[248]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 81)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[249]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 81)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[244]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 82)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[245]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 82)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[246]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 82)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[247]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 82)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[248]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 82)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[249]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 82)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[250]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 82)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[245]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 83)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[246]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 83)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[247]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 83)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[248]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 83)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[249]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 83)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[250]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 83)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[251]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 83)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[252]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 84)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[253]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 84)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[254]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 84)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[255]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 84)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[256]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 84)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[257]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 84)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[258]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 84)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[253]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 85)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[254]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 85)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[255]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 85)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[256]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 85)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[257]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 85)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[258]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 85)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[259]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 85)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[254]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 86)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[255]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 86)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[256]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 86)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[257]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 86)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[258]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 86)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[259]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 86)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[260]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 86)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[261]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 87)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[262]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 87)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[263]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 87)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[264]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 87)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[265]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 87)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[266]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 87)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[267]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 87)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[262]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 88)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[263]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 88)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[264]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 88)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[265]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 88)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[266]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 88)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[267]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 88)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[268]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 88)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[263]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 89)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[264]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 89)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[265]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 89)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[266]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 89)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[267]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 89)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[268]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 89)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[269]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 89)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[270]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 90)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[271]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 90)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[272]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 90)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[273]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 90)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[274]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 90)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[275]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 90)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[276]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 90)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[271]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 91)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[272]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 91)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[273]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 91)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[274]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 91)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[275]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 91)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[276]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 91)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[277]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 91)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[272]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 92)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[273]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 92)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[274]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 92)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[275]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 92)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[276]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 92)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[277]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 92)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[278]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 92)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[279]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 93)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[280]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 93)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[281]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 93)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[282]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 93)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[283]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 93)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[284]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 93)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[285]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 93)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[280]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 94)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[281]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 94)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[282]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 94)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[283]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 94)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[284]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 94)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[285]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 94)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[286]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 94)]))
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[281]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 95)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[282]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 95)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[283]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 95)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[284]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 95)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[285]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 95)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[286]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 95)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[287]*kernel.shared_1[(((threadIdx.x*192) + (ff.outer.inner*96)) + 95)]))
}
}
}
}
}
for (i1.inner: int32, 0, 2) {
- for (i2.inner: int32, 0, 7) {
- compute[(((((blockIdx.x*3136) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[((i1.inner*7) + i2.inner)] + bias[(((blockIdx.x*64) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+ for (i3.inner: int32, 0, 7) {
+ compute[(((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((floordiv(blockIdx.x, 7)*64) + (threadIdx.x*2)) + i1.inner)]), 0f32)
}
}
}
@@ -645,7 +1624,7 @@ cooperative fetching, unrolling and operator fusion.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.333 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.389 ms
</pre></div>
</div>
</div>
@@ -680,19 +1659,19 @@ conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o
conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=32)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
-conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=7)
+conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
-conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
+conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=7)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
-conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
+conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=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=3)
+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_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
-conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
-conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
+conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
@@ -700,11 +1679,11 @@ 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_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
-compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=7)
+compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
-compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
-compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
+compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
+compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -724,14 +1703,14 @@ 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=32)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=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=32)
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", 64)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -749,10 +1728,10 @@ 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__(32) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[14];
- __shared__ float pad_temp_shared[648];
- __shared__ float kernel_shared[4608];
+ __shared__ float pad_temp_shared[288];
+ __shared__ float kernel_shared[6144];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -767,89 +1746,890 @@ 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 < 64; ++rc_outer_outer) {
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((9 <= (((int)threadIdx.x) % 81)) && ((((int)threadIdx.x) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((9 <= ((((int)threadIdx.x) + 62) % 81)) && (((((int)threadIdx.x) + 62) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 81) * 49)) + ((((((int)threadIdx.x) + 62) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 200) {
- pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((9 <= ((((int)threadIdx.x) + 43) % 81)) && (((((int)threadIdx.x) + 43) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 448) / 81) * 49)) + ((((((int)threadIdx.x) + 43) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 224) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 8) % 72))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 448) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 672) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 896) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
- kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1120) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 40) % 72))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1344) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1568) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1792) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
- kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72)) + 129024)];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2240) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 8) % 72))];
- kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2464) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2688) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
- kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2912) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3136) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 40) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3360)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3360) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3584)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3584) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3808)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3808) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
- kernel_shared[(((int)threadIdx.x) + 4032)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72)) + 258048)];
- kernel_shared[(((int)threadIdx.x) + 4256)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4256) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 8) % 72))];
- if (((int)threadIdx.x) < 128) {
- kernel_shared[(((int)threadIdx.x) + 4480)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4480) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
- for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
- 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[(((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 3)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 6)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 9)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 12)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 15)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 3)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 6)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 9)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 12)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 15)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 3)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 6)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 9)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 12)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 15)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 3)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 6)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 9)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 12)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 15)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 3)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 6)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 9)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 12)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 15)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 3)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 6)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 9)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 12)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 15)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 3)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 6)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 9)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 12)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((rc_outer_inner * 162) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 153)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + rx_outer_inner) + 15)]));
- }
+ for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
+ for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 32)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 32) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 64)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 64) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 96)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 96) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 128)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 128) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 160)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 160) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 192)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 192) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 224) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 256)] = (((((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 * 1568) + (((((int)threadIdx.x) + 256) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 32)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 64)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 96)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 4608)];
+ kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 4608)];
+ kernel_shared[(((int)threadIdx.x) + 160)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 4608)];
+ kernel_shared[(((int)threadIdx.x) + 192)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 9216)];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 9216)];
+ kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 9216)];
+ kernel_shared[(((int)threadIdx.x) + 288)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 13824)];
+ kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 13824)];
+ kernel_shared[(((int)threadIdx.x) + 352)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 13824)];
+ kernel_shared[(((int)threadIdx.x) + 384)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 18432)];
+ kernel_shared[(((int)threadIdx.x) + 416)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 18432)];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 18432)];
+ kernel_shared[(((int)threadIdx.x) + 480)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 23040)];
+ kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 23040)];
+ kernel_shared[(((int)threadIdx.x) + 544)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 23040)];
+ kernel_shared[(((int)threadIdx.x) + 576)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 27648)];
+ kernel_shared[(((int)threadIdx.x) + 608)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 27648)];
+ kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 27648)];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 32256)];
+ kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 32256)];
+ kernel_shared[(((int)threadIdx.x) + 736)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 32256)];
+ kernel_shared[(((int)threadIdx.x) + 768)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 800)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 864)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 41472)];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 41472)];
+ kernel_shared[(((int)threadIdx.x) + 928)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 41472)];
+ kernel_shared[(((int)threadIdx.x) + 960)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 46080)];
+ kernel_shared[(((int)threadIdx.x) + 992)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 46080)];
+ kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 46080)];
+ kernel_shared[(((int)threadIdx.x) + 1056)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 50688)];
+ kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 50688)];
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 50688)];
+ kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 55296)];
+ kernel_shared[(((int)threadIdx.x) + 1184)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 55296)];
+ kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 55296)];
+ kernel_shared[(((int)threadIdx.x) + 1248)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 59904)];
+ kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 59904)];
+ kernel_shared[(((int)threadIdx.x) + 1312)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 59904)];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 1376)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 1440)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 69120)];
+ kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 69120)];
+ kernel_shared[(((int)threadIdx.x) + 1504)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 69120)];
+ kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 1632)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 78336)];
+ kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 78336)];
+ kernel_shared[(((int)threadIdx.x) + 1696)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 78336)];
+ kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 82944)];
+ kernel_shared[(((int)threadIdx.x) + 1760)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 82944)];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 82944)];
+ kernel_shared[(((int)threadIdx.x) + 1824)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 87552)];
+ kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 87552)];
+ kernel_shared[(((int)threadIdx.x) + 1888)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 87552)];
+ kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 92160)];
+ kernel_shared[(((int)threadIdx.x) + 1952)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 92160)];
+ kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 92160)];
+ kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 96768)];
+ kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 96768)];
+ kernel_shared[(((int)threadIdx.x) + 2080)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 96768)];
+ kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 101376)];
+ kernel_shared[(((int)threadIdx.x) + 2144)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 101376)];
+ kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 101376)];
+ kernel_shared[(((int)threadIdx.x) + 2208)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 105984)];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 105984)];
+ kernel_shared[(((int)threadIdx.x) + 2272)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 105984)];
+ kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 2336)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 2400)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 115200)];
+ kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 115200)];
+ kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 115200)];
+ kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 119808)];
+ kernel_shared[(((int)threadIdx.x) + 2528)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 119808)];
+ kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 119808)];
+ kernel_shared[(((int)threadIdx.x) + 2592)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 124416)];
+ kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 124416)];
+ kernel_shared[(((int)threadIdx.x) + 2656)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 124416)];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 129024)];
+ kernel_shared[(((int)threadIdx.x) + 2720)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 129024)];
+ kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 129024)];
+ kernel_shared[(((int)threadIdx.x) + 2784)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 133632)];
+ kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 133632)];
+ kernel_shared[(((int)threadIdx.x) + 2848)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 133632)];
+ kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 138240)];
+ kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 138240)];
+ kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 138240)];
+ kernel_shared[(((int)threadIdx.x) + 2976)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 142848)];
+ kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 142848)];
+ kernel_shared[(((int)threadIdx.x) + 3040)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 142848)];
+ kernel_shared[(((int)threadIdx.x) + 3072)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
+ kernel_shared[(((int)threadIdx.x) + 3104)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 147456)];
+ kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 147456)];
+ kernel_shared[(((int)threadIdx.x) + 3168)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 152064)];
+ kernel_shared[(((int)threadIdx.x) + 3200)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 152064)];
+ kernel_shared[(((int)threadIdx.x) + 3232)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 152064)];
+ kernel_shared[(((int)threadIdx.x) + 3264)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 156672)];
+ kernel_shared[(((int)threadIdx.x) + 3296)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 156672)];
+ kernel_shared[(((int)threadIdx.x) + 3328)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 156672)];
+ kernel_shared[(((int)threadIdx.x) + 3360)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 161280)];
+ kernel_shared[(((int)threadIdx.x) + 3392)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 161280)];
+ kernel_shared[(((int)threadIdx.x) + 3424)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 161280)];
+ kernel_shared[(((int)threadIdx.x) + 3456)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 165888)];
+ kernel_shared[(((int)threadIdx.x) + 3488)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 165888)];
+ kernel_shared[(((int)threadIdx.x) + 3520)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 165888)];
+ kernel_shared[(((int)threadIdx.x) + 3552)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 170496)];
+ kernel_shared[(((int)threadIdx.x) + 3584)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 170496)];
+ kernel_shared[(((int)threadIdx.x) + 3616)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 170496)];
+ kernel_shared[(((int)threadIdx.x) + 3648)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 175104)];
+ kernel_shared[(((int)threadIdx.x) + 3680)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 175104)];
+ kernel_shared[(((int)threadIdx.x) + 3712)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 175104)];
+ kernel_shared[(((int)threadIdx.x) + 3744)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 179712)];
+ kernel_shared[(((int)threadIdx.x) + 3776)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 179712)];
+ kernel_shared[(((int)threadIdx.x) + 3808)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 179712)];
+ kernel_shared[(((int)threadIdx.x) + 3840)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
+ kernel_shared[(((int)threadIdx.x) + 3872)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 184320)];
+ kernel_shared[(((int)threadIdx.x) + 3904)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 184320)];
+ kernel_shared[(((int)threadIdx.x) + 3936)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 188928)];
+ kernel_shared[(((int)threadIdx.x) + 3968)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 188928)];
+ kernel_shared[(((int)threadIdx.x) + 4000)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 188928)];
+ kernel_shared[(((int)threadIdx.x) + 4032)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 193536)];
+ kernel_shared[(((int)threadIdx.x) + 4064)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 193536)];
+ kernel_shared[(((int)threadIdx.x) + 4096)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 193536)];
+ kernel_shared[(((int)threadIdx.x) + 4128)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 198144)];
+ kernel_shared[(((int)threadIdx.x) + 4160)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 198144)];
+ kernel_shared[(((int)threadIdx.x) + 4192)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 198144)];
+ kernel_shared[(((int)threadIdx.x) + 4224)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 202752)];
+ kernel_shared[(((int)threadIdx.x) + 4256)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 202752)];
+ kernel_shared[(((int)threadIdx.x) + 4288)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 202752)];
+ kernel_shared[(((int)threadIdx.x) + 4320)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 207360)];
+ kernel_shared[(((int)threadIdx.x) + 4352)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 207360)];
+ kernel_shared[(((int)threadIdx.x) + 4384)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 207360)];
+ kernel_shared[(((int)threadIdx.x) + 4416)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 211968)];
+ kernel_shared[(((int)threadIdx.x) + 4448)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 211968)];
+ kernel_shared[(((int)threadIdx.x) + 4480)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 211968)];
+ kernel_shared[(((int)threadIdx.x) + 4512)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 216576)];
+ kernel_shared[(((int)threadIdx.x) + 4544)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 216576)];
+ kernel_shared[(((int)threadIdx.x) + 4576)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 216576)];
+ kernel_shared[(((int)threadIdx.x) + 4608)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
+ kernel_shared[(((int)threadIdx.x) + 4640)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 221184)];
+ kernel_shared[(((int)threadIdx.x) + 4672)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 221184)];
+ kernel_shared[(((int)threadIdx.x) + 4704)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 225792)];
+ kernel_shared[(((int)threadIdx.x) + 4736)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 225792)];
+ kernel_shared[(((int)threadIdx.x) + 4768)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 225792)];
+ kernel_shared[(((int)threadIdx.x) + 4800)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 230400)];
+ kernel_shared[(((int)threadIdx.x) + 4832)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 230400)];
+ kernel_shared[(((int)threadIdx.x) + 4864)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 230400)];
+ kernel_shared[(((int)threadIdx.x) + 4896)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 235008)];
+ kernel_shared[(((int)threadIdx.x) + 4928)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 235008)];
+ kernel_shared[(((int)threadIdx.x) + 4960)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 235008)];
+ kernel_shared[(((int)threadIdx.x) + 4992)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 239616)];
+ kernel_shared[(((int)threadIdx.x) + 5024)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 239616)];
+ kernel_shared[(((int)threadIdx.x) + 5056)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 239616)];
+ kernel_shared[(((int)threadIdx.x) + 5088)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 244224)];
+ kernel_shared[(((int)threadIdx.x) + 5120)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 244224)];
+ kernel_shared[(((int)threadIdx.x) + 5152)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 244224)];
+ kernel_shared[(((int)threadIdx.x) + 5184)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 248832)];
+ kernel_shared[(((int)threadIdx.x) + 5216)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 248832)];
+ kernel_shared[(((int)threadIdx.x) + 5248)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 248832)];
+ kernel_shared[(((int)threadIdx.x) + 5280)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 253440)];
+ kernel_shared[(((int)threadIdx.x) + 5312)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 253440)];
+ kernel_shared[(((int)threadIdx.x) + 5344)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 253440)];
+ kernel_shared[(((int)threadIdx.x) + 5376)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
+ kernel_shared[(((int)threadIdx.x) + 5408)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 258048)];
+ kernel_shared[(((int)threadIdx.x) + 5440)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 258048)];
+ kernel_shared[(((int)threadIdx.x) + 5472)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 262656)];
+ kernel_shared[(((int)threadIdx.x) + 5504)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 262656)];
+ kernel_shared[(((int)threadIdx.x) + 5536)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 262656)];
+ kernel_shared[(((int)threadIdx.x) + 5568)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 267264)];
+ kernel_shared[(((int)threadIdx.x) + 5600)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 267264)];
+ kernel_shared[(((int)threadIdx.x) + 5632)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 267264)];
+ kernel_shared[(((int)threadIdx.x) + 5664)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 271872)];
+ kernel_shared[(((int)threadIdx.x) + 5696)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 271872)];
+ kernel_shared[(((int)threadIdx.x) + 5728)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 271872)];
+ kernel_shared[(((int)threadIdx.x) + 5760)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 276480)];
+ kernel_shared[(((int)threadIdx.x) + 5792)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 276480)];
+ kernel_shared[(((int)threadIdx.x) + 5824)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 276480)];
+ kernel_shared[(((int)threadIdx.x) + 5856)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 281088)];
+ kernel_shared[(((int)threadIdx.x) + 5888)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 281088)];
+ kernel_shared[(((int)threadIdx.x) + 5920)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 281088)];
+ kernel_shared[(((int)threadIdx.x) + 5952)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 285696)];
+ kernel_shared[(((int)threadIdx.x) + 5984)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 285696)];
+ kernel_shared[(((int)threadIdx.x) + 6016)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 285696)];
+ kernel_shared[(((int)threadIdx.x) + 6048)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 290304)];
+ kernel_shared[(((int)threadIdx.x) + 6080)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 290304)];
+ kernel_shared[(((int)threadIdx.x) + 6112)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 290304)];
+ __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[0] * kernel_shared[((((int)threadIdx.x) * 192) + (ff_outer_inner * 96))]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 192) + (ff_outer_inner * 96))]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 192) + (ff_outer_inner * 96))]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 192) + (ff_outer_inner * 96))]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 192) + (ff_outer_inner * 96))]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 192) + (ff_outer_inner * 96))]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 192) + (ff_outer_inner * 96))]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[1] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 1)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[2] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 1)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[3] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 1)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[4] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 1)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[5] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 1)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[6] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 1)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[7] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 1)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[2] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 2)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[3] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 2)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[4] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 2)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[5] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 2)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[6] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 2)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[7] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 2)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[8] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 2)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[9] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 3)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[10] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 3)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[11] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 3)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[12] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 3)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[13] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 3)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[14] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 3)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[15] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 3)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[10] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 4)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[11] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 4)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[12] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 4)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[13] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 4)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[14] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 4)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[15] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 4)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[16] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 4)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[11] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 5)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[12] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 5)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[13] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 5)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[14] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 5)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[15] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 5)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[16] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 5)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[17] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 5)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[18] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 6)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[19] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 6)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[20] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 6)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[21] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 6)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[22] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 6)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[23] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 6)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[24] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 6)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[19] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 7)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[20] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 7)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[21] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 7)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[22] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 7)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[23] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 7)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[24] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 7)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[25] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 7)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[20] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 8)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[21] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 8)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[22] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 8)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[23] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 8)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[24] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 8)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[25] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 8)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[26] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 8)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[27] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 9)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[28] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 9)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[29] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 9)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[30] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 9)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[31] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 9)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[32] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 9)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[33] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 9)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[28] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 10)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[29] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 10)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[30] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 10)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[31] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 10)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[32] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 10)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[33] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 10)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[34] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 10)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[29] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 11)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[30] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 11)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[31] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 11)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[32] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 11)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[33] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 11)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[34] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 11)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[35] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 11)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[36] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 12)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[37] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 12)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[38] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 12)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[39] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 12)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[40] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 12)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[41] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 12)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[42] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 12)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[37] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 13)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[38] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 13)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[39] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 13)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[40] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 13)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[41] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 13)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[42] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 13)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[43] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 13)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[38] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 14)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[39] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 14)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[40] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 14)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[41] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 14)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[42] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 14)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[43] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 14)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[44] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 14)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[45] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 15)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[46] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 15)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[47] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 15)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[48] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 15)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[49] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 15)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[50] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 15)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[51] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 15)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[46] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 16)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[47] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 16)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[48] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 16)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[49] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 16)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[50] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 16)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[51] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 16)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[52] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 16)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[47] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 17)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[48] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 17)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[49] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 17)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[50] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 17)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[51] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 17)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[52] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 17)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[53] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 17)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[54] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 18)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[55] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 18)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[56] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 18)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[57] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 18)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[58] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 18)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[59] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 18)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[60] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 18)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[55] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 19)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[56] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 19)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[57] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 19)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[58] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 19)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[59] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 19)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[60] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 19)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[61] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 19)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[56] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 20)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[57] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 20)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[58] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 20)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[59] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 20)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[60] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 20)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[61] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 20)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[62] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 20)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[63] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 21)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[64] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 21)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[65] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 21)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[66] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 21)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[67] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 21)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[68] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 21)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[69] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 21)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[64] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 22)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[65] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 22)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[66] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 22)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[67] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 22)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[68] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 22)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[69] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 22)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[70] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 22)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[65] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 23)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[66] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 23)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[67] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 23)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[68] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 23)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[69] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 23)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[70] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 23)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[71] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 23)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[72] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 24)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[73] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 24)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[74] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 24)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[75] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 24)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[76] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 24)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[77] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 24)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[78] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 24)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[73] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 25)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[74] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 25)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[75] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 25)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[76] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 25)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[77] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 25)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[78] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 25)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[79] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 25)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[74] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 26)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[75] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 26)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[76] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 26)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[77] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 26)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[78] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 26)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[79] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 26)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[80] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 26)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[81] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 27)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[82] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 27)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[83] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 27)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[84] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 27)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[85] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 27)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[86] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 27)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[87] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 27)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[82] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 28)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[83] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 28)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[84] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 28)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[85] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 28)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[86] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 28)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[87] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 28)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[88] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 28)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[83] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 29)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[84] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 29)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[85] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 29)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[86] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 29)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[87] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 29)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[88] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 29)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[89] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 29)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[90] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 30)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[91] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 30)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[92] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 30)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[93] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 30)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[94] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 30)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[95] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 30)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[96] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 30)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[91] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 31)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[92] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 31)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[93] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 31)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[94] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 31)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[95] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 31)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[96] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 31)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[97] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 31)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[92] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 32)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[93] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 32)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[94] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 32)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[95] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 32)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[96] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 32)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[97] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 32)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[98] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 32)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[99] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 33)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[100] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 33)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[101] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 33)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[102] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 33)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[103] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 33)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[104] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 33)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[105] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 33)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[100] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 34)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[101] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 34)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[102] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 34)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[103] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 34)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[104] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 34)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[105] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 34)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[106] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 34)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[101] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 35)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[102] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 35)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[103] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 35)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[104] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 35)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[105] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 35)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[106] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 35)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[107] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 35)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[108] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 36)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[109] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 36)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[110] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 36)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[111] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 36)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[112] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 36)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[113] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 36)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[114] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 36)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[109] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 37)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[110] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 37)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[111] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 37)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[112] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 37)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[113] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 37)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[114] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 37)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[115] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 37)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[110] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 38)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[111] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 38)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[112] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 38)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[113] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 38)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[114] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 38)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[115] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 38)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[116] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 38)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[117] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 39)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[118] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 39)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[119] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 39)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[120] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 39)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[121] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 39)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[122] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 39)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[123] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 39)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[118] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 40)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[119] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 40)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[120] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 40)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[121] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 40)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[122] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 40)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[123] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 40)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[124] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 40)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[119] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 41)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[120] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 41)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[121] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 41)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[122] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 41)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[123] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 41)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[124] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 41)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[125] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 41)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[126] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 42)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[127] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 42)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[128] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 42)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[129] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 42)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[130] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 42)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[131] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 42)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[132] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 42)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[127] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 43)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[128] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 43)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[129] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 43)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[130] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 43)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[131] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 43)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[132] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 43)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[133] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 43)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[128] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 44)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[129] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 44)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[130] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 44)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[131] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 44)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[132] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 44)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[133] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 44)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[134] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 44)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[135] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 45)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[136] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 45)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[137] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 45)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[138] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 45)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[139] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 45)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[140] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 45)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[141] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 45)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[136] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 46)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[137] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 46)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[138] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 46)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[139] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 46)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[140] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 46)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[141] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 46)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[142] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 46)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[137] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 47)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[138] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 47)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[139] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 47)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[140] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 47)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[141] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 47)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[142] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 47)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[143] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 47)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[144] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 48)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[145] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 48)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[146] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 48)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[147] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 48)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[148] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 48)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[149] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 48)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[150] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 48)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[145] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 49)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[146] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 49)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[147] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 49)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[148] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 49)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[149] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 49)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[150] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 49)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[151] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 49)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[146] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 50)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[147] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 50)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[148] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 50)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[149] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 50)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[150] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 50)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[151] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 50)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[152] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 50)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[153] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 51)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[154] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 51)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[155] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 51)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[156] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 51)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[157] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 51)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[158] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 51)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[159] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 51)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[154] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 52)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[155] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 52)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[156] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 52)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[157] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 52)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[158] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 52)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[159] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 52)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[160] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 52)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[155] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 53)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[156] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 53)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[157] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 53)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[158] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 53)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[159] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 53)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[160] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 53)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[161] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 53)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[162] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 54)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[163] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 54)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[164] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 54)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[165] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 54)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[166] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 54)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[167] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 54)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[168] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 54)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[163] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 55)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[164] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 55)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[165] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 55)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[166] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 55)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[167] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 55)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[168] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 55)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[169] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 55)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[164] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 56)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[165] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 56)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[166] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 56)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[167] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 56)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[168] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 56)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[169] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 56)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[170] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 56)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[171] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 57)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[172] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 57)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[173] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 57)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[174] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 57)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[175] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 57)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[176] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 57)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[177] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 57)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[172] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 58)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[173] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 58)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[174] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 58)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[175] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 58)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[176] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 58)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[177] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 58)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[178] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 58)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[173] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 59)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[174] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 59)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[175] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 59)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[176] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 59)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[177] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 59)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[178] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 59)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[179] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 59)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[180] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 60)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[181] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 60)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[182] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 60)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[183] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 60)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[184] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 60)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[185] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 60)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[186] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 60)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[181] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 61)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[182] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 61)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[183] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 61)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[184] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 61)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[185] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 61)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[186] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 61)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[187] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 61)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[182] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 62)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[183] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 62)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[184] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 62)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[185] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 62)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[186] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 62)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[187] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 62)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[188] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 62)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[189] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 63)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[190] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 63)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[191] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 63)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[192] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 63)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[193] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 63)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[194] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 63)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[195] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 63)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[190] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 64)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[191] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 64)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[192] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 64)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[193] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 64)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[194] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 64)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[195] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 64)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[196] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 64)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[191] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 65)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[192] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 65)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[193] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 65)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[194] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 65)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[195] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 65)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[196] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 65)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[197] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 65)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[198] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 66)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[199] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 66)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[200] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 66)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[201] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 66)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[202] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 66)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[203] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 66)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[204] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 66)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[199] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 67)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[200] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 67)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[201] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 67)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[202] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 67)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[203] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 67)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[204] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 67)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[205] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 67)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[200] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 68)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[201] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 68)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[202] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 68)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[203] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 68)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[204] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 68)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[205] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 68)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[206] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 68)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[207] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 69)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[208] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 69)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[209] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 69)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[210] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 69)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[211] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 69)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[212] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 69)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[213] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 69)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[208] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 70)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[209] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 70)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[210] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 70)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[211] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 70)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[212] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 70)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[213] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 70)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[214] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 70)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[209] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 71)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[210] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 71)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[211] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 71)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[212] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 71)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[213] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 71)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[214] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 71)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[215] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 71)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[216] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 72)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[217] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 72)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[218] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 72)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[219] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 72)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[220] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 72)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[221] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 72)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[222] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 72)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[217] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 73)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[218] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 73)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[219] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 73)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[220] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 73)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[221] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 73)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[222] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 73)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[223] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 73)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[218] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 74)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[219] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 74)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[220] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 74)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[221] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 74)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[222] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 74)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[223] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 74)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[224] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 74)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[225] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 75)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[226] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 75)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[227] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 75)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[228] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 75)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[229] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 75)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[230] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 75)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[231] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 75)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[226] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 76)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[227] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 76)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[228] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 76)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[229] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 76)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[230] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 76)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[231] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 76)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[232] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 76)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[227] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 77)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[228] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 77)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[229] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 77)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[230] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 77)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[231] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 77)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[232] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 77)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[233] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 77)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[234] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 78)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[235] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 78)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[236] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 78)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[237] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 78)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[238] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 78)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[239] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 78)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[240] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 78)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[235] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 79)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[236] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 79)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[237] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 79)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[238] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 79)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[239] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 79)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[240] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 79)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[241] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 79)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[236] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 80)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[237] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 80)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[238] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 80)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[239] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 80)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[240] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 80)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[241] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 80)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[242] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 80)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[243] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 81)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[244] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 81)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[245] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 81)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[246] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 81)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[247] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 81)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[248] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 81)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[249] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 81)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[244] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 82)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[245] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 82)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[246] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 82)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[247] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 82)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[248] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 82)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[249] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 82)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[250] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 82)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[245] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 83)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[246] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 83)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[247] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 83)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[248] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 83)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[249] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 83)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[250] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 83)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[251] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 83)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[252] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 84)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[253] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 84)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[254] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 84)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[255] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 84)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[256] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 84)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[257] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 84)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[258] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 84)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[253] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 85)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[254] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 85)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[255] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 85)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[256] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 85)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[257] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 85)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[258] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 85)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[259] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 85)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[254] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 86)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[255] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 86)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[256] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 86)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[257] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 86)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[258] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 86)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[259] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 86)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[260] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 86)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[261] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 87)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[262] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 87)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[263] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 87)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[264] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 87)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[265] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 87)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[266] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 87)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[267] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 87)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[262] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 88)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[263] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 88)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[264] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 88)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[265] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 88)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[266] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 88)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[267] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 88)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[268] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 88)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[263] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 89)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[264] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 89)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[265] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 89)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[266] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 89)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[267] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 89)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[268] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 89)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[269] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 89)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[270] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 90)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[271] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 90)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[272] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 90)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[273] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 90)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[274] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 90)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[275] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 90)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[276] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 90)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[271] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 91)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[272] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 91)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[273] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 91)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[274] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 91)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[275] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 91)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[276] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 91)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[277] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 91)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[272] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 92)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[273] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 92)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[274] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 92)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[275] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 92)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[276] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 92)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[277] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 92)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[278] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 92)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[279] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 93)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[280] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 93)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[281] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 93)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[282] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 93)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[283] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 93)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[284] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 93)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[285] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 93)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[280] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 94)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[281] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 94)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[282] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 94)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[283] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 94)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[284] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 94)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[285] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 94)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[286] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 94)]));
+ conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[281] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 95)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[282] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 95)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[283] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 95)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[284] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 95)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[285] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 95)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[286] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 95)]));
+ conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[287] * kernel_shared[(((((int)threadIdx.x) * 192) + (ff_outer_inner * 96)) + 95)]));
}
}
}
for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
- compute[(((((((int)blockIdx.x) * 3136) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[((i1_inner * 7) + i2_inner)] + bias[(((((int)blockIdx.x) * 64) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
+ compute[((((((((int)blockIdx.x) / 7) * 3136) + (((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) * 64) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
}
}
}
@@ -888,7 +2668,7 @@ In the example below we resume the status and do more 5 trials.</p>
Get devices for measurement successfully!
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 27.817 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 25.793 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/e3e540f3b477c0c52d8eb73e674e8ffd/tune_conv2d_layer_cuda.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tune_conv2d_layer_cuda.py</span></code></a></p>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
index 6eb65de5f..3424e9452 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -876,7 +876,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 9.5788 9.5924 9.6194 9.5246 0.0399
+ 9.9809 9.9759 10.0159 9.9508 0.0268
</pre></div>
</div>
</div>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
index 935e73d8f..4f5aa8c09 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -895,7 +895,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 775.9427 776.4630 778.8285 772.5366 2.5949
+ 764.2532 762.7735 768.1185 761.8676 2.7581
</pre></div>
</div>
</div>
@@ -917,7 +917,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 19.903 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 20.595 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-network-x86-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/e416b94ca1090b0897c0f6e0df95b911/tune_network_x86.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tune_network_x86.py</span></code></a></p>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
index 3f05dfe9a..838a3f64c 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -600,74 +600,80 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], [])} {
- for (i0.outer: int32, 0, 16) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [128]), storage_scope = global;
- for (i1.outer: int32, 0, 32) {
- for (i.inner.init: int32, 0, 8) {
- let cse_var_1: int32 = (i.inner.init*16)
- {
- compute_5: Buffer(compute_4, float32, [128], [])[cse_var_1] = 0f32
- compute_5[(cse_var_1 + 1)] = 0f32
- compute_5[(cse_var_1 + 2)] = 0f32
- compute_5[(cse_var_1 + 3)] = 0f32
- compute_5[(cse_var_1 + 4)] = 0f32
- compute_5[(cse_var_1 + 5)] = 0f32
- compute_5[(cse_var_1 + 6)] = 0f32
- compute_5[(cse_var_1 + 7)] = 0f32
- compute_5[(cse_var_1 + 8)] = 0f32
- compute_5[(cse_var_1 + 9)] = 0f32
- compute_5[(cse_var_1 + 10)] = 0f32
- compute_5[(cse_var_1 + 11)] = 0f32
- compute_5[(cse_var_1 + 12)] = 0f32
- compute_5[(cse_var_1 + 13)] = 0f32
- compute_5[(cse_var_1 + 14)] = 0f32
- compute_5[(cse_var_1 + 15)] = 0f32
- }
- }
- for (elem_idx: int32, 0, (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])) {
- for (i.inner: int32, 0, 8) {
- let cse_var_19: int32 = (i.inner*16)
- let cse_var_18: int32 = (elem_idx*16)
- let cse_var_17: int32 = (cse_var_19 + 1)
- let cse_var_16: int32 = (cse_var_19 + 11)
- let cse_var_15: int32 = (cse_var_19 + 12)
- let cse_var_14: int32 = (cse_var_19 + 13)
- let cse_var_13: int32 = (cse_var_19 + 14)
- let cse_var_12: int32 = (cse_var_19 + 15)
- let cse_var_11: int32 = (cse_var_19 + 2)
- let cse_var_10: int32 = (cse_var_19 + 3)
- let cse_var_9: int32 = (cse_var_19 + 4)
- let cse_var_8: int32 = (cse_var_19 + 5)
- let cse_var_7: int32 = (cse_var_19 + 6)
- let cse_var_6: int32 = (cse_var_19 + 7)
- let cse_var_5: int32 = (cse_var_19 + 8)
- let cse_var_4: int32 = (cse_var_19 + 9)
- let cse_var_3: int32 = (cse_var_19 + 10)
- let cse_var_2: int32 = ((i0.outer*2048) + (i.inner*256))
- {
- compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[((placeholder_3[i1.outer]*16) + cse_var_18)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 1)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 2)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 3)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 4)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 5)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 6)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 7)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 8)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 9)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 10)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 11)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 12)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 13)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 14)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 15)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
+ preflattened_buffer_map = {placeholder_8: placeholder_15: Buffer(placeholder_13, int32, [33], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 32) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 8) {
+ for (nb_j.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 8) {
+ let cse_var_1: int32 = (((i.outer.inner*256) + (i.inner.init*32)) + (nb_j.inner*16))
+ {
+ compute_5: Buffer(compute_4, float32, [2048], [])[cse_var_1] = 0f32
+ compute_5[(cse_var_1 + 1)] = 0f32
+ compute_5[(cse_var_1 + 2)] = 0f32
+ compute_5[(cse_var_1 + 3)] = 0f32
+ compute_5[(cse_var_1 + 4)] = 0f32
+ compute_5[(cse_var_1 + 5)] = 0f32
+ compute_5[(cse_var_1 + 6)] = 0f32
+ compute_5[(cse_var_1 + 7)] = 0f32
+ compute_5[(cse_var_1 + 8)] = 0f32
+ compute_5[(cse_var_1 + 9)] = 0f32
+ compute_5[(cse_var_1 + 10)] = 0f32
+ compute_5[(cse_var_1 + 11)] = 0f32
+ compute_5[(cse_var_1 + 12)] = 0f32
+ compute_5[(cse_var_1 + 13)] = 0f32
+ compute_5[(cse_var_1 + 14)] = 0f32
+ compute_5[(cse_var_1 + 15)] = 0f32
+ }
+ }
+ for (elem_idx: int32, 0, let cse_var_2: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
+ for (i.inner: int32, 0, 8) {
+ let cse_var_21: int32 = (elem_idx*16)
+ let cse_var_20: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
+ let cse_var_19: int32 = (((i.outer.inner*256) + (i.inner*32)) + (nb_j.inner*16))
+ let cse_var_18: int32 = (cse_var_19 + 1)
+ let cse_var_17: int32 = (cse_var_19 + 11)
+ let cse_var_16: int32 = (cse_var_19 + 12)
+ let cse_var_15: int32 = (cse_var_19 + 13)
+ let cse_var_14: int32 = (cse_var_19 + 14)
+ let cse_var_13: int32 = (cse_var_19 + 15)
+ let cse_var_12: int32 = (cse_var_19 + 2)
+ let cse_var_11: int32 = (cse_var_19 + 3)
+ let cse_var_10: int32 = (cse_var_19 + 4)
+ let cse_var_9: int32 = (cse_var_19 + 5)
+ let cse_var_8: int32 = (cse_var_19 + 6)
+ let cse_var_7: int32 = (cse_var_19 + 7)
+ let cse_var_6: int32 = (cse_var_19 + 8)
+ let cse_var_5: int32 = (cse_var_19 + 9)
+ let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i.outer.inner*2048)) + (i.inner*256))
+ let cse_var_3: int32 = (cse_var_19 + 10)
+ {
+ compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[((placeholder_3[cse_var_20]*16) + cse_var_21)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ }
+ }
}
}
}
- for (i0.inner: int32, 0, 8) {
- let cse_var_20: int32 = (((i0.outer*4096) + (i0.inner*512)) + (i1.outer*16))
- compute[ramp(cse_var_20, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_20, 1, 16)]), broadcast(0f32, 16))
+ for (i0.inner: int32, 0, 64) {
+ for (i1.inner: int32, 0, 32) {
+ let cse_var_22: int32 = ((((floordiv(i0.outer.i1.outer.fused, 16)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32)) + i1.inner)
+ compute[cse_var_22] = max((compute_5[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_22]), 0f32)
+ }
}
}
}
@@ -706,7 +712,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.829 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.842 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 44e5ed746..e914ce8e5 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -300,13 +300,13 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:44.112</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:45.054</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:43.196</strong>: <a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></li>
-<li><p><strong>00:00.240</strong>: <a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></li>
-<li><p><strong>00:00.229</strong>: <a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></li>
-<li><p><strong>00:00.226</strong>: <a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></li>
-<li><p><strong>00:00.223</strong>: <a class="reference internal" href="tune_relay_mobile_gpu.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-mobile-gpu-py"><span class="std std-ref">Auto-tuning a Convolutional Network for Mobile GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_mobile_gpu.py</span></code>)</p></li>
+<li><p><strong>00:44.125</strong>: <a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></li>
+<li><p><strong>00:00.246</strong>: <a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></li>
+<li><p><strong>00:00.229</strong>: <a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></li>
+<li><p><strong>00:00.227</strong>: <a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></li>
+<li><p><strong>00:00.227</strong>: <a class="reference internal" href="tune_relay_mobile_gpu.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-mobile-gpu-py"><span class="std std-ref">Auto-tuning a Convolutional Network for Mobile GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_mobile_gpu.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
index b228e0acb..d43eaf891 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -1142,8 +1142,8 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2885496
-No: 6 GFLOPS: 42.39/42.39 result: MeasureResult(costs=(0.005461852578947368,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6047112941741943, timestamp=1652876750.7511399) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
-No: 7 GFLOPS: 0.00/42.39 result: Traceback (most recent call last):
+No: 6 GFLOPS: 92.93/92.93 result: MeasureResult(costs=(0.0024911723958333334,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6307353973388672, timestamp=1652876930.0346053) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
+No: 7 GFLOPS: 0.00/92.93 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1266,7 +1266,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6225319
-No: 8 GFLOPS: 0.00/42.39 result: Traceback (most recent call last):
+No: 8 GFLOPS: 0.00/92.93 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1389,7 +1389,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,943546
-No: 9 GFLOPS: 0.00/42.39 result: Traceback (most recent call last):
+No: 9 GFLOPS: 0.00/92.93 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1512,7 +1512,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2868708
-No: 10 GFLOPS: 0.00/42.39 result: Traceback (most recent call last):
+No: 10 GFLOPS: 0.00/92.93 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
res = future.result()
File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
@@ -1530,7 +1530,7 @@ No: 10 GFLOPS: 0.00/42.39 result: Traceback (most recent call last):
TimeoutError
[('tile_f', [-1, 32, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4691833
-No: 11 GFLOPS: 0.00/42.39 result: Traceback (most recent call last):
+No: 11 GFLOPS: 0.00/92.93 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1653,7 +1653,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1042124
-No: 12 GFLOPS: 0.00/42.39 result: Traceback (most recent call last):
+No: 12 GFLOPS: 0.00/92.93 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1776,7 +1776,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10013405
-No: 13 GFLOPS: 0.00/42.39 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/92.93 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1899,7 +1899,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6732082
-No: 14 GFLOPS: 0.00/42.39 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/92.93 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2022,7 +2022,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7536735
-No: 15 GFLOPS: 0.00/42.39 result: Traceback (most recent call last):
+No: 15 GFLOPS: 0.00/92.93 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2145,7 +2145,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,482121
-No: 16 GFLOPS: 0.00/42.39 result: Traceback (most recent call last):
+No: 16 GFLOPS: 0.00/92.93 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2268,7 +2268,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2824525
-No: 17 GFLOPS: 0.00/42.39 result: Traceback (most recent call last):
+No: 17 GFLOPS: 0.00/92.93 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2391,7 +2391,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4559286
-No: 18 GFLOPS: 0.00/42.39 result: Traceback (most recent call last):
+No: 18 GFLOPS: 0.00/92.93 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2514,7 +2514,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9677544
-No: 19 GFLOPS: 0.00/42.39 result: Traceback (most recent call last):
+No: 19 GFLOPS: 0.00/92.93 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 721, in __call__
yield remote, remote.load_module(os.path.split(build_result.filename)[1])
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 685, in run_through_rpc
@@ -2602,7 +2602,7 @@ tvm._ffi.base.TVMError: Traceback (most recent call last):
15: _PyEval_EvalFrameDefault
14: 0x0000000000537c30
13: _PyObject_FastCallKeywords
- 12: 0x00007f7253a78fa2
+ 12: 0x00007fce3ecc1fa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -2667,7 +2667,7 @@ Traceback (most recent call last):
21: _PyFunction_FastCallKeywords
20: _PyEval_EvalFrameDefault
19: _PyFunction_FastCall [('tile_f', [-1, 8, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6390073
-No: 20 GFLOPS: 143.67/143.67 result: MeasureResult(costs=(0.0016113597301587303,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1335551738739014, timestamp=1652876776.9256022) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
+No: 20 GFLOPS: 143.43/143.43 result: MeasureResult(costs=(0.00161398642,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.435722827911377, timestamp=1652876955.858234) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2706,7 +2706,7 @@ and measure running time.</p>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Best config:
[('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
-Time cost of this operator: 0.001995
+Time cost of this operator: 0.001988
</pre></div>
</div>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autotvm-tune-conv2d-cuda-py">
diff --git a/docs/how_to/work_with_microtvm/micro_autotune.html b/docs/how_to/work_with_microtvm/micro_autotune.html
index 1c3d2fa0c..ec58f307d 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -553,10 +553,10 @@ the tuned operator.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 501.9 99.098 (1, 2, 10, 10, 3) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.466 0.684 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 1.101 0.217 (1, 1, 10, 10, 3) 1 1
-Total_time - 506.467 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 314.1 98.755 (1, 2, 10, 10, 3) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.058 0.961 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.901 0.283 (1, 1, 10, 10, 3) 1 1
+Total_time - 318.058 - - - -
</pre></div>
</div>
</div>
@@ -608,10 +608,10 @@ Total_time -
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 80.75 96.809 (1, 6, 10, 10, 1) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.753 2.102 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.908 1.089 (1, 1, 10, 10, 3) 1 1
-Total_time - 83.412 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 80.75 96.855 (1, 6, 10, 10, 1) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.702 2.041 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.92 1.104 (1, 1, 10, 10, 3) 1 1
+Total_time - 83.372 - - - -
</pre></div>
</div>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/sg_execution_times.html b/docs/how_to/work_with_microtvm/sg_execution_times.html
index e5574feee..0059f9522 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -300,13 +300,13 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:46.852</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>00:48.029</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:42.591</strong>: <a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></li>
-<li><p><strong>00:03.646</strong>: <a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></li>
-<li><p><strong>00:00.213</strong>: <a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></li>
-<li><p><strong>00:00.202</strong>: <a class="reference internal" href="micro_reference_vm.html#sphx-glr-how-to-work-with-microtvm-micro-reference-vm-py"><span class="std std-ref">microTVM Reference Virtual Machines</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_reference_vm.py</span></code>)</p></li>
-<li><p><strong>00:00.200</strong>: <a class="reference internal" href="micro_tvmc.html#sphx-glr-how-to-work-with-microtvm-micro-tvmc-py"><span class="std std-ref">Executing a Tiny Model with TVMC Micro</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tvmc.py</span></code>)</p></li>
+<li><p><strong>00:43.672</strong>: <a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></li>
+<li><p><strong>00:03.732</strong>: <a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></li>
+<li><p><strong>00:00.222</strong>: <a class="reference internal" href="micro_tvmc.html#sphx-glr-how-to-work-with-microtvm-micro-tvmc-py"><span class="std std-ref">Executing a Tiny Model with TVMC Micro</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tvmc.py</span></code>)</p></li>
+<li><p><strong>00:00.204</strong>: <a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></li>
+<li><p><strong>00:00.198</strong>: <a class="reference internal" href="micro_reference_vm.html#sphx-glr-how-to-work-with-microtvm-micro-reference-vm-py"><span class="std std-ref">microTVM Reference Virtual Machines</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_reference_vm.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/how_to/work_with_relay/sg_execution_times.html b/docs/how_to/work_with_relay/sg_execution_times.html
index 9ac858522..2f5a685e4 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -300,11 +300,11 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:08.896</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:08.906</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:06.798</strong>: <a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></li>
-<li><p><strong>00:01.877</strong>: <a class="reference internal" href="build_gcn.html#sphx-glr-how-to-work-with-relay-build-gcn-py"><span class="std std-ref">Building a Graph Convolutional Network</span></a> (<code class="docutils literal notranslate"><span class="pre">build_gcn.py</span></code>)</p></li>
-<li><p><strong>00:00.221</strong>: <a class="reference internal" href="using_relay_viz.html#sphx-glr-how-to-work-with-relay-using-relay-viz-py"><span class="std std-ref">Use Relay Visualizer to Visualize Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_relay_viz.py</span></code>)</p></li>
+<li><p><strong>00:06.834</strong>: <a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></li>
+<li><p><strong>00:01.845</strong>: <a class="reference internal" href="build_gcn.html#sphx-glr-how-to-work-with-relay-build-gcn-py"><span class="std std-ref">Building a Graph Convolutional Network</span></a> (<code class="docutils literal notranslate"><span class="pre">build_gcn.py</span></code>)</p></li>
+<li><p><strong>00:00.228</strong>: <a class="reference internal" href="using_relay_viz.html#sphx-glr-how-to-work-with-relay-using-relay-viz-py"><span class="std std-ref">Use Relay Visualizer to Visualize Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_relay_viz.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/how_to/work_with_schedules/sg_execution_times.html b/docs/how_to/work_with_schedules/sg_execution_times.html
index 72cd2c031..dad0cd3d4 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -300,16 +300,16 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:05.747</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:05.823</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:02.099</strong>: <a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></li>
-<li><p><strong>00:01.153</strong>: <a class="reference internal" href="tensorize.html#sphx-glr-how-to-work-with-schedules-tensorize-py"><span class="std std-ref">Use Tensorize to Leverage Hardware Intrinsics</span></a> (<code class="docutils literal notranslate"><span class="pre">tensorize.py</span></code>)</p></li>
-<li><p><strong>00:00.743</strong>: <a class="reference internal" href="reduction.html#sphx-glr-how-to-work-with-schedules-reduction-py"><span class="std std-ref">Reduction</span></a> (<code class="docutils literal notranslate"><span class="pre">reduction.py</span></code>)</p></li>
-<li><p><strong>00:00.715</strong>: <a class="reference internal" href="scan.html#sphx-glr-how-to-work-with-schedules-scan-py"><span class="std std-ref">Scan and Recurrent Kernel</span></a> (<code class="docutils literal notranslate"><span class="pre">scan.py</span></code>)</p></li>
-<li><p><strong>00:00.313</strong>: <a class="reference internal" href="extern_op.html#sphx-glr-how-to-work-with-schedules-extern-op-py"><span class="std std-ref">External Tensor Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">extern_op.py</span></code>)</p></li>
-<li><p><strong>00:00.252</strong>: <a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></li>
-<li><p><strong>00:00.242</strong>: <a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></li>
-<li><p><strong>00:00.230</strong>: <a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></li>
+<li><p><strong>00:02.130</strong>: <a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></li>
+<li><p><strong>00:01.156</strong>: <a class="reference internal" href="tensorize.html#sphx-glr-how-to-work-with-schedules-tensorize-py"><span class="std std-ref">Use Tensorize to Leverage Hardware Intrinsics</span></a> (<code class="docutils literal notranslate"><span class="pre">tensorize.py</span></code>)</p></li>
+<li><p><strong>00:00.745</strong>: <a class="reference internal" href="reduction.html#sphx-glr-how-to-work-with-schedules-reduction-py"><span class="std std-ref">Reduction</span></a> (<code class="docutils literal notranslate"><span class="pre">reduction.py</span></code>)</p></li>
+<li><p><strong>00:00.733</strong>: <a class="reference internal" href="scan.html#sphx-glr-how-to-work-with-schedules-scan-py"><span class="std std-ref">Scan and Recurrent Kernel</span></a> (<code class="docutils literal notranslate"><span class="pre">scan.py</span></code>)</p></li>
+<li><p><strong>00:00.320</strong>: <a class="reference internal" href="extern_op.html#sphx-glr-how-to-work-with-schedules-extern-op-py"><span class="std std-ref">External Tensor Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">extern_op.py</span></code>)</p></li>
+<li><p><strong>00:00.254</strong>: <a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></li>
+<li><p><strong>00:00.251</strong>: <a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></li>
+<li><p><strong>00:00.233</strong>: <a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 2fd2abe8e..ce09dfe51 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -552,7 +552,7 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp_3e83st1/input0.cc'\nsource_filename = \"/tmp/tmp_3e83st1/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/tmpr5uifka1/input0.cc'\nsource_filename = \"/tmp/tmpr5uifka1/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 aa9963c32..54423681a 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1715,7 +1715,7 @@ Can be the a function or the function name.</p></li>
<dl class="py function">
<dt class="sig sig-object py" id="tvm.auto_scheduler.auto_schedule">
-<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
<dd><p>THIS API IS DEPRECATED.</p>
<p>Run auto scheduling search for a task.</p>
<dl class="field-list simple">
@@ -1752,7 +1752,7 @@ the initial naive schedule (state).</p>
<dl class="py class">
<dt class="sig sig-object py" id="tvm.auto_scheduler.SketchPolicy">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
<dd><p>The search policy that searches in a hierarchical search space defined by sketches.
The policy randomly samples programs from the space defined by sketches and use evolutionary
search to fine-tune them.</p>
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index 27f8de0a6..1420d3808 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/dd986fd98/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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 177eb7c15..3c0d125c7 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/dd986fd98/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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 2c8d42dd7..6150d6bf7 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/dd986fd98/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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 65c8c222a..ad41ba6ec 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/dd986fd98/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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 9698d05bd..4004e9ca4 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/dd986fd98/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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 68d8805bf..724e23eef 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/dd986fd98/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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 d3bb4a11f..596f857a8 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/dd986fd98/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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 2c6a34f4b..8da35dcd4 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/dd986fd98/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -698,7 +698,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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 78222dfd1..5682efd35 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/dd986fd98/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/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/dd986fd98/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/memory.ts#L53">memory.ts:53</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -462,7 +462,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/memory.ts#L114">memory.ts:114</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -485,7 +485,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/memory.ts#L124">memory.ts:124</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -502,7 +502,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/memory.ts#L175">memory.ts:175</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/module.html b/docs/reference/api/typedoc/classes/module.html
index 783a19c4c..500ab07ef 100644
--- a/docs/reference/api/typedoc/classes/module.html
+++ b/docs/reference/api/typedoc/classes/module.html
@@ -124,7 +124,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L504">runtime.ts:504</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L502">runtime.ts:502</a></li>
</ul>
</aside>
</section>
@@ -187,7 +187,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L516">runtime.ts:516</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -204,7 +204,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L530">runtime.ts:530</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -236,7 +236,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L561">runtime.ts:561</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/ndarray.html b/docs/reference/api/typedoc/classes/ndarray.html
index 4e9e8d5af..ceb06c143 100644
--- a/docs/reference/api/typedoc/classes/ndarray.html
+++ b/docs/reference/api/typedoc/classes/ndarray.html
@@ -130,7 +130,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L304">runtime.ts:304</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -158,7 +158,7 @@
<div class="tsd-signature tsd-kind-icon">device<span class="tsd-signature-symbol">:</span> <a href="dldevice.html" class="tsd-signature-type">DLDevice</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L297">runtime.ts:297</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -173,7 +173,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L293">runtime.ts:293</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -188,7 +188,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L289">runtime.ts:289</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -203,7 +203,7 @@
<div class="tsd-signature tsd-kind-icon">ndim<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L291">runtime.ts:291</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -218,7 +218,7 @@
<div class="tsd-signature tsd-kind-icon">shape<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L295">runtime.ts:295</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -240,7 +240,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L370">runtime.ts:370</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -273,7 +273,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L414">runtime.ts:414</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -305,7 +305,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L355">runtime.ts:355</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -322,7 +322,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L474">runtime.ts:474</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -346,7 +346,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L443">runtime.ts:443</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/packedfunccell.html b/docs/reference/api/typedoc/classes/packedfunccell.html
index ef7b7b301..c350060d8 100644
--- a/docs/reference/api/typedoc/classes/packedfunccell.html
+++ b/docs/reference/api/typedoc/classes/packedfunccell.html
@@ -122,7 +122,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L158">runtime.ts:158</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -147,7 +147,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L157">runtime.ts:157</a></li>
</ul>
</aside>
</section>
@@ -164,7 +164,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L165">runtime.ts:165</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
diff --git a/docs/reference/api/typedoc/classes/rpcserver.html b/docs/reference/api/typedoc/classes/rpcserver.html
index 9cb452a70..e75cc7f14 100644
--- a/docs/reference/api/typedoc/classes/rpcserver.html
+++ b/docs/reference/api/typedoc/classes/rpcserver.html
@@ -115,7 +115,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">get<wbr>Imports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">unknown</span><span class="tsd-signat [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -201,7 +201,7 @@
<div class="tsd-signature tsd-kind-icon">key<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
</ul>
</aside>
</section>
@@ -211,7 +211,7 @@
<div class="tsd-signature tsd-kind-icon">logger<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>msg<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -242,7 +242,7 @@
<div class="tsd-signature tsd-kind-icon">socket<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">WebSocket</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
</ul>
</aside>
</section>
@@ -252,7 +252,7 @@
<div class="tsd-signature tsd-kind-icon">state<span class="tsd-signature-symbol">:</span> <a href="../enums/rpcserverstate.html" class="tsd-signature-type">RPCServerState</a><span class="tsd-signature-symbol"> = RPCServerState.InitHeader</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
</ul>
</aside>
</section>
@@ -262,7 +262,7 @@
<div class="tsd-signature tsd-kind-icon">url<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/classes/scalar.html b/docs/reference/api/typedoc/classes/scalar.html
index 490fff982..d07d8a247 100644
--- a/docs/reference/api/typedoc/classes/scalar.html
+++ b/docs/reference/api/typedoc/classes/scalar.html
@@ -112,7 +112,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -137,7 +137,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -152,7 +152,7 @@
<div class="tsd-signature tsd-kind-icon">value<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L143">runtime.ts:143</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/webgpucontext.html b/docs/reference/api/typedoc/classes/webgpucontext.html
index fda1d96c4..d455f1935 100644
--- a/docs/reference/api/typedoc/classes/webgpucontext.html
+++ b/docs/reference/api/typedoc/classes/webgpucontext.html
@@ -120,7 +120,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -145,7 +145,7 @@
<div class="tsd-signature tsd-kind-icon">device<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">GPUDevice</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
</ul>
</aside>
</section>
@@ -155,7 +155,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
</ul>
</aside>
</section>
@@ -172,7 +172,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -209,7 +209,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/enums/argtypecode.html b/docs/reference/api/typedoc/enums/argtypecode.html
index 02d8a4276..f6d13c9b2 100644
--- a/docs/reference/api/typedoc/enums/argtypecode.html
+++ b/docs/reference/api/typedoc/enums/argtypecode.html
@@ -106,7 +106,7 @@
<div class="tsd-signature tsd-kind-icon">DLDevice<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 6</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
</ul>
</aside>
</section>
@@ -116,7 +116,7 @@
<div class="tsd-signature tsd-kind-icon">Float<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
</ul>
</aside>
</section>
@@ -126,7 +126,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
</ul>
</aside>
</section>
@@ -136,7 +136,7 @@
<div class="tsd-signature tsd-kind-icon">Null<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
</ul>
</aside>
</section>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">TVMBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 12</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
</ul>
</aside>
</section>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">TVMDLTensor<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">TVMData<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 5</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">TVMModule<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 9</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">TVMNDArray<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 13</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
</ul>
</aside>
</section>
@@ -196,7 +196,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObject<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
</ul>
</aside>
</section>
@@ -206,7 +206,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObjectRValue<wbr>Ref<wbr>Arg<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 14</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
</ul>
</aside>
</section>
@@ -216,7 +216,7 @@
<div class="tsd-signature tsd-kind-icon">TVMOpaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
</ul>
</aside>
</section>
@@ -226,7 +226,7 @@
<div class="tsd-signature tsd-kind-icon">TVMPacked<wbr>Func<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 10</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
</ul>
</aside>
</section>
@@ -236,7 +236,7 @@
<div class="tsd-signature tsd-kind-icon">TVMStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 11</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
</ul>
</aside>
</section>
@@ -246,7 +246,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/aynccallbackcode.html b/docs/reference/api/typedoc/enums/aynccallbackcode.html
index 690ad55dc..777fe9089 100644
--- a/docs/reference/api/typedoc/enums/aynccallbackcode.html
+++ b/docs/reference/api/typedoc/enums/aynccallbackcode.html
@@ -93,7 +93,7 @@
<div class="tsd-signature tsd-kind-icon">k<wbr>Exception<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 5</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L676">runtime.ts:676</a></li>
</ul>
</aside>
</section>
@@ -103,7 +103,7 @@
<div class="tsd-signature tsd-kind-icon">k<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L675">runtime.ts:675</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/dldatatypecode.html b/docs/reference/api/typedoc/enums/dldatatypecode.html
index 42183799f..9486e5cc7 100644
--- a/docs/reference/api/typedoc/enums/dldatatypecode.html
+++ b/docs/reference/api/typedoc/enums/dldatatypecode.html
@@ -95,7 +95,7 @@
<div class="tsd-signature tsd-kind-icon">Float<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L242">runtime.ts:242</a></li>
</ul>
</aside>
</section>
@@ -105,7 +105,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L240">runtime.ts:240</a></li>
</ul>
</aside>
</section>
@@ -115,7 +115,7 @@
<div class="tsd-signature tsd-kind-icon">Opaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L243">runtime.ts:243</a></li>
</ul>
</aside>
</section>
@@ -125,7 +125,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L241">runtime.ts:241</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/rpcserverstate.html b/docs/reference/api/typedoc/enums/rpcserverstate.html
index 26533c668..9fb561b07 100644
--- a/docs/reference/api/typedoc/enums/rpcserverstate.html
+++ b/docs/reference/api/typedoc/enums/rpcserverstate.html
@@ -90,7 +90,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Header<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
</ul>
</aside>
</section>
@@ -100,7 +100,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Header<wbr>Key<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Server<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Body<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Header<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">Wait<wbr>For<wbr>Callback<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/sizeof.html b/docs/reference/api/typedoc/enums/sizeof.html
index 4503b0a39..632125081 100644
--- a/docs/reference/api/typedoc/enums/sizeof.html
+++ b/docs/reference/api/typedoc/enums/sizeof.html
@@ -100,7 +100,7 @@
<div class="tsd-signature tsd-kind-icon">DLData<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = I32</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">DLDevice<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = I32 + I32</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">F32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">F64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">I32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
</ul>
</aside>
</section>
@@ -150,7 +150,7 @@
<div class="tsd-signature tsd-kind-icon">I64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
</ul>
</aside>
</section>
@@ -160,7 +160,7 @@
<div class="tsd-signature tsd-kind-icon">TVMValue<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
</ul>
</aside>
</section>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">U16<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
</ul>
</aside>
</section>
@@ -180,7 +180,7 @@
<div class="tsd-signature tsd-kind-icon">U8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/index.html b/docs/reference/api/typedoc/index.html
index 5987653c9..dc21d6cd2 100644
--- a/docs/reference/api/typedoc/index.html
+++ b/docs/reference/api/typedoc/index.html
@@ -174,7 +174,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Alloc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>shape<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, ndim<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeCode<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeBits<span class="tsd [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>Bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">num [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -282,7 +282,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>To<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>from<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, to<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-sig [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -326,7 +326,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>ToBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</sp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -370,7 +370,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -406,7 +406,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMBackend<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number< [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -458,7 +458,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCFunc<wbr>Set<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ret<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -506,7 +506,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCb<wbr>Arg<wbr>ToReturn<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, code<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span c [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -545,7 +545,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Call<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -601,7 +601,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -637,7 +637,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Get<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span cla [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -676,7 +676,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>List<wbr>Global<wbr>Names<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>outSize<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, outArray<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -715,7 +715,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Register<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, f<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, override<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</spa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -758,7 +758,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMGet<wbr>Last<wbr>Error<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -788,7 +788,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -824,7 +824,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Get<wbr>Function<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, funcName<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, queryImports<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">numbe [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -872,7 +872,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Import<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, dep<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-si [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -912,7 +912,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMSynchronize<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>deviceType<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, deviceId<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signatur [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -954,7 +954,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Alloc<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>size<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -990,7 +990,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Free<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ptr<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1026,7 +1026,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Func<wbr>Create<wbr>FromCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resource<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1066,7 +1066,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>args<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1118,7 +1118,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<wbr>Finalizer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resourceHandle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1154,7 +1154,7 @@
<div class="tsd-signature tsd-kind-icon">GPUPointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1169,7 +1169,7 @@
<div class="tsd-signature tsd-kind-icon">Packed<wbr>Func<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">...</span>args<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol"> & </span><a href="interfaces/disp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L36">runtime.ts:36</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1184,7 +1184,7 @@
<div class="tsd-signature tsd-kind-icon">Pointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1199,7 +1199,7 @@
<div class="tsd-signature tsd-kind-icon">Ptr<wbr>Offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1217,7 +1217,7 @@
<div class="tsd-signature tsd-kind-icon">RPC_<wbr>MAGIC<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">1045105</span><span class="tsd-signature-symbol"> = 1045105</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1239,7 +1239,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/support.ts#L25">support.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1271,7 +1271,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/support.ts#L39">support.ts:39</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1300,7 +1300,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/support.ts#L52">support.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1337,7 +1337,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/compact.ts#L38">compact.ts:38</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1368,7 +1368,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1390,7 +1390,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/environment.ts#L32">environment.ts:32</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1421,7 +1421,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/compact.ts#L24">compact.ts:24</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1443,7 +1443,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L1356">runtime.ts:1356</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L1356">runtime.ts:1356</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1508,7 +1508,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/support.ts#L62">support.ts:62</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1530,7 +1530,7 @@
<div class="tsd-signature tsd-kind-icon">DLData<wbr>Type<wbr>Code<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L246">runtime.ts:246</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1539,7 +1539,7 @@
<div class="tsd-signature tsd-kind-icon">0<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "int"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L247">runtime.ts:247</a></li>
</ul>
</aside>
</section>
@@ -1549,7 +1549,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "uint"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L248">runtime.ts:248</a></li>
</ul>
</aside>
</section>
@@ -1559,7 +1559,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "float"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L249">runtime.ts:249</a></li>
</ul>
</aside>
</section>
@@ -1569,7 +1569,7 @@
<div class="tsd-signature tsd-kind-icon">3<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "handle"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L250">runtime.ts:250</a></li>
</ul>
</aside>
</section>
@@ -1580,7 +1580,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Enum<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L175">runtime.ts:175</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1589,7 +1589,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L176">runtime.ts:176</a></li>
</ul>
</aside>
</section>
@@ -1599,7 +1599,7 @@
<div class="tsd-signature tsd-kind-icon">15<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "webgpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L180">runtime.ts:180</a></li>
</ul>
</aside>
</section>
@@ -1609,7 +1609,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cuda"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L177">runtime.ts:177</a></li>
</ul>
</aside>
</section>
@@ -1619,7 +1619,7 @@
<div class="tsd-signature tsd-kind-icon">4<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "opencl"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L178">runtime.ts:178</a></li>
</ul>
</aside>
</section>
@@ -1629,7 +1629,7 @@
<div class="tsd-signature tsd-kind-icon">8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "metal"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L179">runtime.ts:179</a></li>
</ul>
</aside>
</section>
@@ -1640,7 +1640,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Str<wbr>ToEnum<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L183">runtime.ts:183</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1649,7 +1649,7 @@
<div class="tsd-signature tsd-kind-icon">cl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L186">runtime.ts:186</a></li>
</ul>
</aside>
</section>
@@ -1659,7 +1659,7 @@
<div class="tsd-signature tsd-kind-icon">cpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L184">runtime.ts:184</a></li>
</ul>
</aside>
</section>
@@ -1669,7 +1669,7 @@
<div class="tsd-signature tsd-kind-icon">cuda<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L185">runtime.ts:185</a></li>
</ul>
</aside>
</section>
@@ -1679,7 +1679,7 @@
<div class="tsd-signature tsd-kind-icon">metal<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L189">runtime.ts:189</a></li>
</ul>
</aside>
</section>
@@ -1689,7 +1689,7 @@
<div class="tsd-signature tsd-kind-icon">opencl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L187">runtime.ts:187</a></li>
</ul>
</aside>
</section>
@@ -1699,7 +1699,7 @@
<div class="tsd-signature tsd-kind-icon">vulkan<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L188">runtime.ts:188</a></li>
</ul>
</aside>
</section>
@@ -1709,7 +1709,7 @@
<div class="tsd-signature tsd-kind-icon">webgpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 15</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/runtime.ts#L190">runtime.ts:190</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/interfaces/disposable.html b/docs/reference/api/typedoc/interfaces/disposable.html
index c86677b06..d96c2ec34 100644
--- a/docs/reference/api/typedoc/interfaces/disposable.html
+++ b/docs/reference/api/typedoc/interfaces/disposable.html
@@ -113,7 +113,7 @@
<div class="tsd-signature tsd-kind-icon">dispose<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/types.ts#L52">types.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/interfaces/functioninfo.html b/docs/reference/api/typedoc/interfaces/functioninfo.html
index 47aaa318b..32bfc724a 100644
--- a/docs/reference/api/typedoc/interfaces/functioninfo.html
+++ b/docs/reference/api/typedoc/interfaces/functioninfo.html
@@ -95,7 +95,7 @@
<div class="tsd-signature tsd-kind-icon">arg_<wbr>types<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
</ul>
</aside>
</section>
@@ -105,7 +105,7 @@
<div class="tsd-signature tsd-kind-icon">launch_<wbr>param_<wbr>tags<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
</ul>
</aside>
</section>
@@ -115,7 +115,7 @@
<div class="tsd-signature tsd-kind-icon">name<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/interfaces/libraryprovider.html b/docs/reference/api/typedoc/interfaces/libraryprovider.html
index 5a1d48f5c..c356b7f46 100644
--- a/docs/reference/api/typedoc/interfaces/libraryprovider.html
+++ b/docs/reference/api/typedoc/interfaces/libraryprovider.html
@@ -112,7 +112,7 @@
<div class="tsd-signature tsd-kind-icon">imports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/types.ts#L34">types.ts:34</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -127,7 +127,7 @@
<div class="tsd-signature tsd-kind-icon">start<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>inst<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">Instance</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/dd986fd98/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/99caa6533/web/src/types.ts#L39">types.ts:39</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/searchindex.js b/docs/searchindex.js
index f00b71da1..63ebc4bd6 100644
--- a/docs/searchindex.js
+++ b/docs/searchindex.js
@@ -1 +1 @@
-Search.setIndex({docnames:["arch/benchmark","arch/convert_layout","arch/debugger","arch/device_target_interactions","arch/frontend/tensorflow","arch/hybrid_script","arch/index","arch/inferbound","arch/introduction_to_module_serialization","arch/microtvm_design","arch/microtvm_project_api","arch/model_library_format","arch/pass_infra","arch/relay_intro","arch/relay_op_strategy","arch/runtime","arch/runtimes/vulkan","arch/security","arch/virtual_machine","contribute/ci","contribute/code_gu [...]
\ No newline at end of file
+Search.setIndex({docnames:["arch/benchmark","arch/convert_layout","arch/debugger","arch/device_target_interactions","arch/frontend/tensorflow","arch/hybrid_script","arch/index","arch/inferbound","arch/introduction_to_module_serialization","arch/microtvm_design","arch/microtvm_project_api","arch/model_library_format","arch/pass_infra","arch/relay_intro","arch/relay_op_strategy","arch/runtime","arch/runtimes/vulkan","arch/security","arch/virtual_machine","contribute/ci","contribute/code_gu [...]
\ No newline at end of file
diff --git a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
index 893c26db9..5c47a80fa 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -300,10 +300,10 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:20.828</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:20.872</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:20.618</strong>: <a class="reference internal" href="tune_relay_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-relay-vta-py"><span class="std std-ref">Auto-tuning a convolutional network on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_vta.py</span></code>)</p></li>
-<li><p><strong>00:00.210</strong>: <a class="reference internal" href="tune_alu_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-alu-vta-py"><span class="std std-ref">Auto-tuning a ALU fused op on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_alu_vta.py</span></code>)</p></li>
+<li><p><strong>00:20.664</strong>: <a class="reference internal" href="tune_relay_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-relay-vta-py"><span class="std std-ref">Auto-tuning a convolutional network on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_vta.py</span></code>)</p></li>
+<li><p><strong>00:00.208</strong>: <a class="reference internal" href="tune_alu_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-alu-vta-py"><span class="std std-ref">Auto-tuning a ALU fused op on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_alu_vta.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_classification.html b/docs/topic/vta/tutorials/frontend/deploy_classification.html
index 12b14fe49..949525a6a 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -539,7 +539,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
-resnet18_v1 inference graph built in 22.17s!
+resnet18_v1 inference graph built in 21.89s!
</pre></div>
</div>
</div>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_detection.html b/docs/topic/vta/tutorials/frontend/deploy_detection.html
index 044162dca..5977a5a74 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -557,7 +557,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/relay/build_module.py:431: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
-yolov3-tiny inference graph built in 15.30s!
+yolov3-tiny inference graph built in 15.33s!
</pre></div>
</div>
</div>
diff --git a/docs/topic/vta/tutorials/frontend/sg_execution_times.html b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
index e22f58a15..9046e7197 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -300,10 +300,10 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-frontend-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>01:28.883</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:28.954</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:46.643</strong>: <a class="reference internal" href="deploy_detection.html#sphx-glr-topic-vta-tutorials-frontend-deploy-detection-py"><span class="std std-ref">Deploy Pretrained Vision Detection Model from Darknet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_detection.py</span></code>)</p></li>
-<li><p><strong>00:42.240</strong>: <a class="reference internal" href="deploy_classification.html#sphx-glr-topic-vta-tutorials-frontend-deploy-classification-py"><span class="std std-ref">Deploy Pretrained Vision Model from MxNet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_classification.py</span></code>)</p></li>
+<li><p><strong>00:47.111</strong>: <a class="reference internal" href="deploy_detection.html#sphx-glr-topic-vta-tutorials-frontend-deploy-detection-py"><span class="std std-ref">Deploy Pretrained Vision Detection Model from Darknet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_detection.py</span></code>)</p></li>
+<li><p><strong>00:41.844</strong>: <a class="reference internal" href="deploy_classification.html#sphx-glr-topic-vta-tutorials-frontend-deploy-classification-py"><span class="std std-ref">Deploy Pretrained Vision Model from MxNet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_classification.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/topic/vta/tutorials/optimize/sg_execution_times.html b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
index 62f1bda4f..23e62199a 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -300,10 +300,10 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-optimize-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:03.526</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.537</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:02.980</strong>: <a class="reference internal" href="convolution_opt.html#sphx-glr-topic-vta-tutorials-optimize-convolution-opt-py"><span class="std std-ref">2D Convolution Optimization</span></a> (<code class="docutils literal notranslate"><span class="pre">convolution_opt.py</span></code>)</p></li>
-<li><p><strong>00:00.546</strong>: <a class="reference internal" href="matrix_multiply_opt.html#sphx-glr-topic-vta-tutorials-optimize-matrix-multiply-opt-py"><span class="std std-ref">Matrix Multiply Blocking</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply_opt.py</span></code>)</p></li>
+<li><p><strong>00:02.986</strong>: <a class="reference internal" href="convolution_opt.html#sphx-glr-topic-vta-tutorials-optimize-convolution-opt-py"><span class="std std-ref">2D Convolution Optimization</span></a> (<code class="docutils literal notranslate"><span class="pre">convolution_opt.py</span></code>)</p></li>
+<li><p><strong>00:00.550</strong>: <a class="reference internal" href="matrix_multiply_opt.html#sphx-glr-topic-vta-tutorials-optimize-matrix-multiply-opt-py"><span class="std std-ref">Matrix Multiply Blocking</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply_opt.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/topic/vta/tutorials/sg_execution_times.html b/docs/topic/vta/tutorials/sg_execution_times.html
index 67fef9839..ce6438dd3 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -300,10 +300,10 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:01.003</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:01.015</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:00.507</strong>: <a class="reference internal" href="matrix_multiply.html#sphx-glr-topic-vta-tutorials-matrix-multiply-py"><span class="std std-ref">Simple Matrix Multiply</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply.py</span></code>)</p></li>
-<li><p><strong>00:00.496</strong>: <a class="reference internal" href="vta_get_started.html#sphx-glr-topic-vta-tutorials-vta-get-started-py"><span class="std std-ref">Get Started with VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">vta_get_started.py</span></code>)</p></li>
+<li><p><strong>00:00.516</strong>: <a class="reference internal" href="matrix_multiply.html#sphx-glr-topic-vta-tutorials-matrix-multiply-py"><span class="std std-ref">Simple Matrix Multiply</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply.py</span></code>)</p></li>
+<li><p><strong>00:00.499</strong>: <a class="reference internal" href="vta_get_started.html#sphx-glr-topic-vta-tutorials-vta-get-started-py"><span class="std std-ref">Get Started with VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">vta_get_started.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/tutorial/auto_scheduler_matmul_x86.html b/docs/tutorial/auto_scheduler_matmul_x86.html
index 2972d4f9f..9e04314af 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -545,7 +545,7 @@ operator fusion.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 92.860 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 95.797 ms
</pre></div>
</div>
</div>
@@ -611,6 +611,7 @@ resume the status and do more 5 trials.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Resume search:
/usr/local/lib/python3.7/dist-packages/xgboost/training.py:17: UserWarning: Old style callback is deprecated. See: https://xgboost.readthedocs.io/en/latest/python/callbacks.html
warnings.warn(f'Old style callback is deprecated. See: {link}', UserWarning)
+*E
</pre></div>
</div>
</div>
@@ -621,6 +622,7 @@ automatically optimize a matrix multiplication, without the need to specify a
search template. It ends a series of examples that starts from the Tensor
Expression (TE) language that demonstrates how TVM can optimize computational
operations.</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.129 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-auto-scheduler-matmul-x86-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../_downloads/eac4389b114db015e95cb3cdf8b86b83/auto_scheduler_matmul_x86.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">auto_scheduler_matmul_x86.py</span></code></a></p>
diff --git a/docs/tutorial/autotvm_relay_x86.html b/docs/tutorial/autotvm_relay_x86.html
index 9661bb066..c0f3790a0 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -516,7 +516,7 @@ standard deviation.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 495.6507313199995, 'median': 495.76053245000367, 'std': 0.8591542303632894}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 499.62126257000136, 'median': 499.6272475500007, 'std': 0.5690515703481694}
</pre></div>
</div>
</div>
@@ -670,179 +670,179 @@ depending on the specifics of the model and the target platform.</p>
</div>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 1/25] Current/Best: 17.21/ 17.21 GFLOPS | Progress: (4/20) | 5.99 s
-[Task 1/25] Current/Best: 6.17/ 17.21 GFLOPS | Progress: (8/20) | 8.94 s
-[Task 1/25] Current/Best: 11.53/ 22.80 GFLOPS | Progress: (12/20) | 11.44 s
-[Task 1/25] Current/Best: 16.87/ 22.80 GFLOPS | Progress: (16/20) | 13.12 s
-[Task 1/25] Current/Best: 11.60/ 23.91 GFLOPS | Progress: (20/20) | 14.85 s Done.
+[Task 1/25] Current/Best: 17.35/ 17.35 GFLOPS | Progress: (4/20) | 6.18 s
+[Task 1/25] Current/Best: 6.10/ 17.35 GFLOPS | Progress: (8/20) | 9.09 s
+[Task 1/25] Current/Best: 11.48/ 22.64 GFLOPS | Progress: (12/20) | 11.54 s
+[Task 1/25] Current/Best: 16.63/ 22.64 GFLOPS | Progress: (16/20) | 13.24 s
+[Task 1/25] Current/Best: 11.55/ 23.80 GFLOPS | Progress: (20/20) | 14.98 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 11.87/ 13.05 GFLOPS | Progress: (4/20) | 3.72 s
-[Task 2/25] Current/Best: 13.95/ 18.11 GFLOPS | Progress: (8/20) | 5.03 s
-[Task 2/25] Current/Best: 20.90/ 20.90 GFLOPS | Progress: (12/20) | 6.38 s
-[Task 2/25] Current/Best: 12.47/ 20.90 GFLOPS | Progress: (16/20) | 7.65 s
-[Task 2/25] Current/Best: 20.19/ 20.90 GFLOPS | Progress: (20/20) | 9.27 s Done.
+[Task 2/25] Current/Best: 12.28/ 12.85 GFLOPS | Progress: (4/20) | 3.82 s
+[Task 2/25] Current/Best: 14.41/ 18.55 GFLOPS | Progress: (8/20) | 5.15 s
+[Task 2/25] Current/Best: 21.13/ 21.13 GFLOPS | Progress: (12/20) | 6.49 s
+[Task 2/25] Current/Best: 11.76/ 21.13 GFLOPS | Progress: (16/20) | 7.80 s
+[Task 2/25] Current/Best: 20.09/ 21.13 GFLOPS | Progress: (20/20) | 9.39 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 3/25] Current/Best: 1.62/ 10.52 GFLOPS | Progress: (4/20) | 5.85 s
-[Task 3/25] Current/Best: 15.52/ 16.86 GFLOPS | Progress: (8/20) | 7.77 s
-[Task 3/25] Current/Best: 14.85/ 16.86 GFLOPS | Progress: (12/20) | 9.48 s
-[Task 3/25] Current/Best: 7.17/ 23.76 GFLOPS | Progress: (16/20) | 11.37 s
-[Task 3/25] Current/Best: 12.54/ 23.76 GFLOPS | Progress: (20/20) | 15.93 s Done.
+[Task 3/25] Current/Best: 1.63/ 10.55 GFLOPS | Progress: (4/20) | 5.84 s
+[Task 3/25] Current/Best: 15.49/ 16.80 GFLOPS | Progress: (8/20) | 7.75 s
+[Task 3/25] Current/Best: 14.83/ 16.80 GFLOPS | Progress: (12/20) | 9.48 s
+[Task 3/25] Current/Best: 7.18/ 23.69 GFLOPS | Progress: (16/20) | 11.41 s
+[Task 3/25] Current/Best: 12.48/ 23.69 GFLOPS | Progress: (20/20) | 15.91 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 9.55/ 20.31 GFLOPS | Progress: (4/20) | 2.31 s
-[Task 4/25] Current/Best: 6.85/ 20.31 GFLOPS | Progress: (8/20) | 7.00 s
-[Task 4/25] Current/Best: 21.78/ 21.78 GFLOPS | Progress: (12/20) | 12.15 s
-[Task 4/25] Current/Best: 17.34/ 21.78 GFLOPS | Progress: (16/20) | 14.66 s
-[Task 4/25] Current/Best: 12.87/ 21.78 GFLOPS | Progress: (20/20) | 16.87 s Done.
+[Task 4/25] Current/Best: 9.56/ 20.32 GFLOPS | Progress: (4/20) | 2.34 s
+[Task 4/25] Current/Best: 6.27/ 20.32 GFLOPS | Progress: (8/20) | 6.74 s
+[Task 4/25] Current/Best: 21.22/ 21.22 GFLOPS | Progress: (12/20) | 11.34 s
+[Task 4/25] Current/Best: 17.10/ 21.22 GFLOPS | Progress: (16/20) | 13.57 s
+[Task 4/25] Current/Best: 13.22/ 21.22 GFLOPS | Progress: (20/20) | 15.49 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 9.69/ 10.26 GFLOPS | Progress: (4/20) | 2.68 s
-[Task 5/25] Current/Best: 11.48/ 12.07 GFLOPS | Progress: (8/20) | 4.96 s
-[Task 5/25] Current/Best: 11.44/ 18.09 GFLOPS | Progress: (12/20) | 8.42 s
-[Task 5/25] Current/Best: 11.62/ 22.56 GFLOPS | Progress: (16/20) | 9.86 s
-[Task 5/25] Current/Best: 11.90/ 22.56 GFLOPS | Progress: (20/20) | 11.78 s Done.
+[Task 5/25] Current/Best: 9.50/ 10.12 GFLOPS | Progress: (4/20) | 2.55 s
+[Task 5/25] Current/Best: 11.62/ 12.96 GFLOPS | Progress: (8/20) | 4.62 s
+[Task 5/25] Current/Best: 10.55/ 17.98 GFLOPS | Progress: (12/20) | 7.75 s
+[Task 5/25] Current/Best: 11.66/ 22.60 GFLOPS | Progress: (16/20) | 9.17 s
+[Task 5/25] Current/Best: 11.95/ 22.60 GFLOPS | Progress: (20/20) | 11.06 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 12.18/ 20.67 GFLOPS | Progress: (4/20) | 4.04 s
-[Task 6/25] Current/Best: 18.99/ 20.67 GFLOPS | Progress: (8/20) | 5.79 s
-[Task 6/25] Current/Best: 13.28/ 20.67 GFLOPS | Progress: (12/20) | 7.74 s
-[Task 6/25] Current/Best: 19.90/ 20.67 GFLOPS | Progress: (16/20) | 9.97 s
-[Task 6/25] Current/Best: 3.75/ 20.67 GFLOPS | Progress: (20/20) | 12.52 s Done.
+[Task 6/25] Current/Best: 12.21/ 20.75 GFLOPS | Progress: (4/20) | 3.95 s
+[Task 6/25] Current/Best: 18.88/ 20.75 GFLOPS | Progress: (8/20) | 5.71 s
+[Task 6/25] Current/Best: 13.27/ 20.75 GFLOPS | Progress: (12/20) | 7.64 s
+[Task 6/25] Current/Best: 19.95/ 20.75 GFLOPS | Progress: (16/20) | 9.90 s
+[Task 6/25] Current/Best: 3.74/ 20.75 GFLOPS | Progress: (20/20) | 12.40 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 11.16/ 12.90 GFLOPS | Progress: (4/20) | 3.57 s
-[Task 7/25] Current/Best: 20.15/ 21.00 GFLOPS | Progress: (8/20) | 5.08 s
-[Task 7/25] Current/Best: 15.30/ 21.00 GFLOPS | Progress: (12/20) | 7.00 s
-[Task 7/25] Current/Best: 12.24/ 21.00 GFLOPS | Progress: (16/20) | 9.06 s
-[Task 7/25] Current/Best: 6.32/ 21.77 GFLOPS | Progress: (20/20) | 11.50 s Done.
+[Task 7/25] Current/Best: 11.18/ 12.14 GFLOPS | Progress: (4/20) | 3.62 s
+[Task 7/25] Current/Best: 20.24/ 20.98 GFLOPS | Progress: (8/20) | 5.13 s
+[Task 7/25] Current/Best: 14.24/ 20.98 GFLOPS | Progress: (12/20) | 7.09 s
+[Task 7/25] Current/Best: 12.23/ 20.98 GFLOPS | Progress: (16/20) | 9.15 s
+[Task 7/25] Current/Best: 6.36/ 21.67 GFLOPS | Progress: (20/20) | 11.63 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 10.17/ 13.67 GFLOPS | Progress: (4/20) | 2.84 s
-[Task 8/25] Current/Best: 9.74/ 13.67 GFLOPS | Progress: (8/20) | 8.02 s
-[Task 8/25] Current/Best: 12.37/ 13.67 GFLOPS | Progress: (12/20) | 14.51 s
-[Task 8/25] Current/Best: 18.88/ 18.88 GFLOPS | Progress: (16/20) | 16.62 s
-[Task 8/25] Current/Best: 19.35/ 19.35 GFLOPS | Progress: (20/20) | 23.79 s Done.
+[Task 8/25] Current/Best: 10.17/ 14.24 GFLOPS | Progress: (4/20) | 2.86 s
+[Task 8/25] Current/Best: 10.27/ 14.24 GFLOPS | Progress: (8/20) | 7.62 s
+[Task 8/25] Current/Best: 12.95/ 14.24 GFLOPS | Progress: (12/20) | 13.82 s
+[Task 8/25] Current/Best: 19.00/ 19.00 GFLOPS | Progress: (16/20) | 15.90 s
+[Task 8/25] Current/Best: 20.00/ 20.00 GFLOPS | Progress: (20/20) | 22.47 s Done.
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 14.33/ 15.66 GFLOPS | Progress: (4/20) | 19.40 s
-[Task 9/25] Current/Best: 23.05/ 23.05 GFLOPS | Progress: (8/20) | 21.15 s
-[Task 9/25] Current/Best: 8.25/ 23.05 GFLOPS | Progress: (12/20) | 23.72 s
-[Task 9/25] Current/Best: 18.01/ 23.05 GFLOPS | Progress: (16/20) | 26.57 s
-[Task 9/25] Current/Best: 9.05/ 23.05 GFLOPS | Progress: (20/20) | 35.26 s
+[Task 9/25] Current/Best: 14.20/ 14.20 GFLOPS | Progress: (4/20) | 17.97 s
+[Task 9/25] Current/Best: 23.21/ 23.21 GFLOPS | Progress: (8/20) | 19.75 s
+[Task 9/25] Current/Best: 8.25/ 23.21 GFLOPS | Progress: (12/20) | 22.14 s
+[Task 9/25] Current/Best: 17.98/ 23.21 GFLOPS | Progress: (16/20) | 24.74 s
+[Task 9/25] Current/Best: 8.97/ 23.21 GFLOPS | Progress: (20/20) | 32.61 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
... 416 lines suppressed ...