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 2023/01/12 06:05:56 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@079876ed5412e7f8beb4c8e82248cca461781ee2)

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 5d9a9f055f deploying docs (apache/tvm@079876ed5412e7f8beb4c8e82248cca461781ee2)
5d9a9f055f is described below

commit 5d9a9f055ffbead2fe9d3794d610e0ccfa79d405
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Thu Jan 12 06:05:50 2023 +0000

    deploying docs (apache/tvm@079876ed5412e7f8beb4c8e82248cca461781ee2)
---
 .../how_to/compile_models/from_darknet.rst.txt     |    2 +-
 .../how_to/compile_models/from_keras.rst.txt       |    2 +-
 .../how_to/compile_models/from_mxnet.rst.txt       |    2 +-
 .../how_to/compile_models/from_oneflow.rst.txt     |    2 +-
 .../how_to/compile_models/from_onnx.rst.txt        |    2 +-
 .../how_to/compile_models/from_pytorch.rst.txt     |    2 +-
 .../how_to/compile_models/from_tensorflow.rst.txt  |    2 +-
 .../compile_models/sg_execution_times.rst.txt      |   22 +-
 .../deploy_models/deploy_model_on_adreno.rst.txt   |    2 +-
 .../deploy_models/deploy_model_on_android.rst.txt  |    2 +-
 .../deploy_object_detection_pytorch.rst.txt        |    4 +-
 .../deploy_models/deploy_prequantized.rst.txt      |    6 +-
 .../deploy_prequantized_tflite.rst.txt             |    4 +-
 .../how_to/deploy_models/deploy_quantized.rst.txt  |    2 +-
 .../deploy_models/deploy_ssd_gluoncv.rst.txt       |    4 +-
 .../deploy_models/sg_execution_times.rst.txt       |   20 +-
 .../extend_tvm/bring_your_own_datatypes.rst.txt    |    2 +-
 .../how_to/extend_tvm/sg_execution_times.rst.txt   |   10 +-
 .../how_to/extend_tvm/use_pass_instrument.rst.txt  |   16 +-
 .../optimize_operators/opt_conv_cuda.rst.txt       |    2 +-
 .../optimize_operators/opt_conv_tensorcore.rst.txt |    2 +-
 .../how_to/optimize_operators/opt_gemm.rst.txt     |   16 +-
 .../optimize_operators/sg_execution_times.rst.txt  |    8 +-
 .../sg_execution_times.rst.txt                     |   14 +-
 .../tune_conv2d_layer_cuda.rst.txt                 | 2997 ++++++++++++++------
 .../tune_network_cuda.rst.txt                      |    4 +-
 .../tune_network_x86.rst.txt                       |    4 +-
 .../tune_sparse_x86.rst.txt                        |   90 +-
 .../tune_with_autotvm/sg_execution_times.rst.txt   |    6 +-
 .../tune_with_autotvm/tune_conv2d_cuda.rst.txt     |  941 +++---
 .../work_with_microtvm/micro_autotune.rst.txt      |   16 +-
 .../work_with_microtvm/micro_pytorch.rst.txt       |    4 +-
 .../how_to/work_with_microtvm/micro_train.rst.txt  |   16 +-
 .../work_with_microtvm/sg_execution_times.rst.txt  |   12 +-
 .../work_with_relay/sg_execution_times.rst.txt     |   10 +-
 .../how_to/work_with_schedules/intrin_math.rst.txt |    2 +-
 .../work_with_schedules/sg_execution_times.rst.txt |   16 +-
 .../how_to/work_with_schedules/tensorize.rst.txt   |    2 +-
 .../tutorials/autotvm/sg_execution_times.rst.txt   |    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     |   11 +-
 docs/_sources/tutorial/autotvm_matmul_x86.rst.txt  |   20 +-
 docs/_sources/tutorial/autotvm_relay_x86.rst.txt   |   57 +-
 .../tutorial/cross_compilation_and_rpc.rst.txt     |    2 +-
 docs/_sources/tutorial/intro_topi.rst.txt          |    2 +-
 docs/_sources/tutorial/sg_execution_times.rst.txt  |   24 +-
 .../tutorial/tensor_expr_get_started.rst.txt       |   47 +-
 docs/commit_hash                                   |    2 +-
 docs/how_to/compile_models/from_darknet.html       |    2 +-
 docs/how_to/compile_models/from_keras.html         |    2 +-
 docs/how_to/compile_models/from_mxnet.html         |    2 +-
 docs/how_to/compile_models/from_oneflow.html       |   18 +-
 docs/how_to/compile_models/from_onnx.html          |    2 +-
 docs/how_to/compile_models/from_pytorch.html       |   10 +-
 docs/how_to/compile_models/from_tensorflow.html    |    2 +-
 docs/how_to/compile_models/sg_execution_times.html |   22 +-
 .../deploy_models/deploy_model_on_adreno.html      |    2 +-
 .../deploy_models/deploy_model_on_android.html     |    2 +-
 .../deploy_object_detection_pytorch.html           |   41 +-
 docs/how_to/deploy_models/deploy_prequantized.html |    9 +-
 .../deploy_models/deploy_prequantized_tflite.html  |    4 +-
 docs/how_to/deploy_models/deploy_quantized.html    |    2 +-
 docs/how_to/deploy_models/deploy_ssd_gluoncv.html  |   37 +-
 docs/how_to/deploy_models/sg_execution_times.html  |   20 +-
 .../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                    | 2997 ++++++++++++++------
 .../tune_with_autoscheduler/tune_network_cuda.html |    4 +-
 .../tune_with_autoscheduler/tune_network_x86.html  |    4 +-
 .../tune_with_autoscheduler/tune_sparse_x86.html   |   90 +-
 .../tune_with_autotvm/sg_execution_times.html      |    6 +-
 .../how_to/tune_with_autotvm/tune_conv2d_cuda.html |  941 +++---
 docs/how_to/work_with_microtvm/micro_autotune.html |   16 +-
 docs/how_to/work_with_microtvm/micro_pytorch.html  |    5 +-
 docs/how_to/work_with_microtvm/micro_train.html    |   16 +-
 .../work_with_microtvm/sg_execution_times.html     |   12 +-
 .../how_to/work_with_relay/sg_execution_times.html |   10 +-
 docs/how_to/work_with_schedules/intrin_math.html   |    2 +-
 .../work_with_schedules/sg_execution_times.html    |   16 +-
 docs/how_to/work_with_schedules/tensorize.html     |    2 +-
 docs/reference/api/python/auto_scheduler.html      |    4 +-
 docs/reference/api/python/relay/frontend.html      |    6 +-
 .../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       |    7 +-
 docs/tutorial/autotvm_matmul_x86.html              |   20 +-
 docs/tutorial/autotvm_relay_x86.html               |  273 +-
 docs/tutorial/cross_compilation_and_rpc.html       |    2 +-
 docs/tutorial/intro_topi.html                      |    2 +-
 docs/tutorial/sg_execution_times.html              |   24 +-
 docs/tutorial/tensor_expr_get_started.html         |   43 +-
 130 files changed, 5860 insertions(+), 3838 deletions(-)

diff --git a/docs/_sources/how_to/compile_models/from_darknet.rst.txt b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
index 256176b8bc..0966a9dc77 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -319,7 +319,7 @@ The process is no different from other examples.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  12.301 seconds)
+   **Total running time of the script:** ( 1 minutes  9.621 seconds)
 
 
 .. _sphx_glr_download_how_to_compile_models_from_darknet.py:
diff --git a/docs/_sources/how_to/compile_models/from_keras.rst.txt b/docs/_sources/how_to/compile_models/from_keras.rst.txt
index bc4a3fad2f..79f1965ec3 100644
--- a/docs/_sources/how_to/compile_models/from_keras.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_keras.rst.txt
@@ -232,7 +232,7 @@ Look up prediction top 1 index in 1000 class synset.
  .. code-block:: none
 
     Relay top-1 id: 285, class name: Egyptian cat
-
    1/1 [==============================] - ETA: 0s
    1/1 [==============================] - 1s 976ms/step
+
    1/1 [==============================] - ETA: 0s
    1/1 [==============================] - 1s 956ms/step
     Keras top-1 id: 285, class name: Egyptian cat
 
 
diff --git a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
index 0bc092718d..c59c700544 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -116,7 +116,7 @@ In this section, we download a pretrained imagenet model and classify an image.
 
  .. code-block:: none
 
-    Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip57274787-008f-47be-ad9d-620e897c12fe from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+    Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipebcec47a-9d37-4a89-a9f8-ed9e09b03c8f 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 6915e3cdba..a1ae8a3339 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -121,7 +121,7 @@ Load a pretrained OneFlow model and save model
  .. code-block:: none
 
     Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
      0%|          | 0.00/41.5M [00:00<?, ?B/s]
     15%|#5        | 6.33M/41.5M [00:00<00:00, 46.7MB/s]
     26%|##6       | 10.8M/41.5M [00:00<00:00, 46.4MB/s]
     37%|###6      | 15.2M/41.5M [00:00<00:00, 43.4MB/s]
     47%|####6     | 19.3M/41.5M [00:00<00:00, 41.8MB/s]
     56%|#####6    | 23.3M/41.5M [00:00<00:00, 40.2MB/s]
     65%|######5   | 27.2M/41.5M [00:00<00:00, 37.7MB/s]
     77%|#######7  | 32.0M/41.5M [00:00<00:00, 41.0MB/s]
     87%|########6 | 36.0M/41.5M [00:00<00:00, 41.4MB/s]
     96%|#########6| 40.0M/41.5M [00:01<00:00, 30.2MB/s]
    100%|##########| 41.5M/41.5M [00:01<00:00, 38.1MB/s]
+
      0%|          | 0.00/41.5M [00:00<?, ?B/s]
     15%|#5        | 6.33M/41.5M [00:00<00:00, 39.3MB/s]
     24%|##4       | 10.1M/41.5M [00:00<00:00, 35.3MB/s]
     39%|###8      | 16.0M/41.5M [00:00<00:00, 43.2MB/s]
     58%|#####7    | 24.0M/41.5M [00:00<00:00, 49.2MB/s]
     69%|######9   | 28.7M/41.5M [00:00<00:00, 45.9MB/s]
     82%|########2 | 34.1M/41.5M [00:00<00:00, 45.0MB/s]
     96%|#########6| 40.0M/41.5M [00:00<00:00, 45.1MB/s]
    100%|##########| 41.5M/41.5M [00:00<00:00, 45.8MB/s]
 
 
 
diff --git a/docs/_sources/how_to/compile_models/from_onnx.rst.txt b/docs/_sources/how_to/compile_models/from_onnx.rst.txt
index 56dbb9ada0..20ba2ebbb7 100644
--- a/docs/_sources/how_to/compile_models/from_onnx.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_onnx.rst.txt
@@ -154,7 +154,7 @@ provides a static definition of the input size.
 
  .. code-block:: none
 
-    /workspace/python/tvm/relay/frontend/onnx.py:6577: UserWarning: Mismatched attribute type in ' : kernel_shape'
+    /workspace/python/tvm/relay/frontend/onnx.py:6689: UserWarning: Mismatched attribute type in ' : kernel_shape'
 
     ==> Context: Bad node spec for node. Name:  OpType: Conv
       warnings.warn(str(e))
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 2981220e57..44d0f28f13 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -102,7 +102,7 @@ Load a pretrained PyTorch model
     /venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=ResNet18_Weights.IMAGENET1K_V1`. You can also use `weights=ResNet18_Weights.DEFAULT` to get the most up-to-date weights.
       warnings.warn(msg)
     Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
-
      0%|          | 0.00/44.7M [00:00<?, ?B/s]
     18%|#7        | 7.99M/44.7M [00:00<00:00, 62.8MB/s]
     36%|###5      | 16.0M/44.7M [00:00<00:00, 59.5MB/s]
     54%|#####4    | 24.1M/44.7M [00:00<00:00, 67.7MB/s]
     79%|#######8  | 35.1M/44.7M [00:00<00:00, 83.9MB/s]
     99%|#########8| 44.2M/44.7M [00:00<00:00, 81.7MB/s]
    100%|##########| 44.7M/44.7M [00:00<00:00, 76.8MB/s]
+
      0%|          | 0.00/44.7M [00:00<?, ?B/s]
     23%|##2       | 10.1M/44.7M [00:00<00:00, 102MB/s]
     52%|#####1    | 23.2M/44.7M [00:00<00:00, 123MB/s]
     78%|#######8  | 35.0M/44.7M [00:00<00:00, 78.6MB/s]
    100%|##########| 44.7M/44.7M [00:00<00:00, 91.9MB/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 eee0f5f0be..7c593d3203 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -425,7 +425,7 @@ Run the corresponding model on tensorflow
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  14.973 seconds)
+   **Total running time of the script:** ( 1 minutes  11.413 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 5247019c8e..5dfb7c82e4 100644
--- a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
 
 Computation times
 =================
-**05:54.740** total execution time for **how_to_compile_models** files:
+**05:42.455** total execution time for **how_to_compile_models** files:
 
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:14.973 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:11.413 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)       | 01:12.301 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)       | 01:09.621 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)         | 00:48.337 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)         | 00:46.396 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)       | 00:33.114 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)       | 00:32.354 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)           | 00:29.348 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)           | 00:29.166 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)         | 00:27.297 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)         | 00:26.574 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)         | 00:25.617 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)         | 00:25.309 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)       | 00:22.907 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)       | 00:22.370 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)           | 00:18.377 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)           | 00:16.812 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)             | 00:02.469 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)             | 00:02.439 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
index e1ff472e95..8c33d0ee2e 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
@@ -728,7 +728,7 @@ well as provides information about the model's performance
     Evaluate inference time cost...
     Execution time summary:
      mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)  
-     2541.2335    2540.7646    2543.7993    2539.9691      1.2031   
+     2542.3069    2542.2529    2545.3980    2540.5547      1.2687   
                
 
 
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 bdb0aa95e7..8c8c2f59ef 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
@@ -437,7 +437,7 @@ Execute on TVM
     Evaluate inference time cost...
     Execution time summary:
      mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)  
-      17.0063      17.0883      17.4245      16.2265       0.3316   
+      16.3062      15.9608      17.2476      15.7254       0.5920   
                
 
 
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 6270313ce8..63c27606ec 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
@@ -131,7 +131,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
     /venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MaskRCNN_ResNet50_FPN_Weights.COCO_V1`. You can also use `weights=MaskRCNN_ResNet50_FPN_Weights.DEFAULT` to get the most up-to-date weights.
       warnings.warn(msg)
     Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
      0%|          | 0.00/170M [00:00<?, ?B/s]
      4%|3         | 6.30M/170M [00:00<00:03, 55.2MB/s]
      7%|6         | 11.6M/170M [00:00<00:04, 35.2MB/s]
      9%|9         | 16.0M/170M [00:00<00:04, 35.8MB/s]
     12%|#2        | 21.0M/170M [00:00<00:03, 40.9MB/s]
     15%|#4        | 25.2M/170M [00:00<00:03, 41.0MB/s]
     22%|##1       | 37.0M/170M [00:00<00:02, 65.6MB/s]
     28%|##8       | 48.0M/170M [00:00<00:01, 69.0MB/s]
     33%|###3      | 56.7M/170M [00:01<00:01, 75.0MB/s]
     38%|###7      | 64.1M/170M [00:01<00:01, 74.8MB/s]
     45%|####5     | 76.6M/170M [00:01<00:01, 90.6MB/s]
     51%|#####     | 86.6M/170M [00:01<00:00, 94.5MB/s]
     56%|#####6    | 95.8M/170M [00:01<00:00, 93.4MB/s]
     62%|######1   | 105M/170M [00:01<00:00, 70.6MB/s] 
     66%|######6   | 112M/170M [00:01<00:01, 51.8MB/s]
     75%|#######5  | 128M/170M [00:02<00:00, 68.6MB/s]
     80%|########  | 136M/170M [00:02<00:00, 65.2MB/s]
     87%|########6 | 147M/170M [00:02<00:00, 76.5MB/s]
 
     92%|#########1| 156M/170M [00:02<00:00, 66.0MB/s]
     98%|#########8| 167M/170M [00:02<00:00, 77.1MB/s]
    100%|##########| 170M/170M [00:02<00:00, 68.0MB/s]
+
      0%|          | 0.00/170M [00:00<?, ?B/s]
      6%|5         | 10.1M/170M [00:00<00:02, 60.6MB/s]
     13%|#3        | 22.9M/170M [00:00<00:01, 93.9MB/s]
     19%|#9        | 32.8M/170M [00:00<00:01, 78.2MB/s]
     24%|##4       | 41.0M/170M [00:00<00:01, 79.7MB/s]
     33%|###2      | 55.7M/170M [00:00<00:01, 102MB/s] 
     39%|###8      | 66.2M/170M [00:00<00:01, 83.1MB/s]
     44%|####4     | 75.2M/170M [00:00<00:01, 85.9MB/s]
     52%|#####1    | 88.0M/170M [00:01<00:00, 86.6MB/s]
     57%|#####6    | 96.7M/170M [00:01<00:00, 80.4MB/s]
     62%|######1   | 105M/170M [00:01<00:01, 64.9MB/s] 
     66%|######6   | 112M/170M [00:01<00:00, 68.5MB/s]
     72%|#######1  | 122M/170M [00:01<00:00, 76.1MB/s]
     76%|#######6  | 130M/170M [00:01<00:00, 68.1MB/s]
     81%|########  | 137M/170M [00:01<00:00, 55.9MB/s]
     85%|########4 | 144M/170M [00:02<00:00, 59.9MB/s]
     88%|########8 | 150M/170M [00:02<00:00, 58.5MB/s]
     93%|#########3| 158M/170M [00:02<00:00, 64.6MB/s]
    
  97%|#########7| 165M/170M [00:02<00:00, 55.3MB/s]
    100%|##########| 170M/170M [00:02<00:00, 70.6MB/s]
     /venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
       for i in range(dim)
     /venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -300,7 +300,7 @@ Get boxes with score larger than 0.9
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 3 minutes  23.678 seconds)
+   **Total running time of the script:** ( 3 minutes  15.612 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 94aea9df38..f47244ee75 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -240,7 +240,7 @@ training. Other models require a full post training calibration.
     /venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MobileNet_V2_Weights.IMAGENET1K_V1`. You can also use `weights=MobileNet_V2_Weights.DEFAULT` to get the most up-to-date weights.
       warnings.warn(msg)
     Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
      0%|          | 0.00/13.6M [00:00<?, ?B/s]
     47%|####6     | 6.30M/13.6M [00:00<00:00, 56.6MB/s]
     86%|########6 | 11.7M/13.6M [00:00<00:00, 54.1MB/s]
    100%|##########| 13.6M/13.6M [00:00<00:00, 55.4MB/s]
+
      0%|          | 0.00/13.6M [00:00<?, ?B/s]
     59%|#####8    | 7.99M/13.6M [00:00<00:00, 46.8MB/s]
    100%|##########| 13.6M/13.6M [00:00<00:00, 68.7MB/s]
 
 
 
@@ -422,7 +422,7 @@ 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)  
-      90.9066      90.8621      96.1144      90.2798       0.5811   
+      90.1449      90.0781      92.3321      89.9773       0.2632   
                
 
 
@@ -471,7 +471,7 @@ TODO
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  8.878 seconds)
+   **Total running time of the script:** ( 1 minutes  5.543 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 662eb5df46..ee14fb1670 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
@@ -436,7 +436,7 @@ 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)  
-      121.3369     121.3223     127.6271     120.3300      0.7701   
+      120.0660     119.9553     124.2132     119.3955      0.5039   
                
 
 
@@ -473,7 +473,7 @@ 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  23.611 seconds)
+   **Total running time of the script:** ( 2 minutes  21.747 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 00ce7ba69d..59b4127197 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -257,7 +257,7 @@ We create a Relay VM to build and execute the model.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  30.417 seconds)
+   **Total running time of the script:** ( 1 minutes  26.011 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 d955ea25f2..20c0af1531 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
@@ -170,7 +170,7 @@ Convert and compile model for CPU.
             data: None
       input_sym_arg_type = in_param.infer_type()[0]
     Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
      0%|          | 0/132723 [00:00<?, ?KB/s]
      4%|4         | 5735/132723 [00:00<00:02, 57119.22KB/s]
     10%|#         | 13334/132723 [00:00<00:01, 68196.41KB/s]
     16%|#5        | 20661/132723 [00:00<00:01, 70503.38KB/s]
     22%|##1       | 28604/132723 [00:00<00:01, 74022.65KB/s]
     27%|##7       | 36426/132723 [00:00<00:01, 75532.90KB/s]
     33%|###3      | 44292/132723 [00:00<00:01, 76593.27KB/s]
     39%|###9      | 52116/132723 [00:00<00:01, 77125.15KB/s]
     45%|####5     | 59829/132723 [00:00<00:00, 76953.52KB/s]
     51%|#####     | 67525/132723 [00:00<00:00, 76673.45KB/s]
     57%|#####6    | 75193/132723 [00:01<00:00, 76439.33KB/s]
     62%|######2   | 82838/132723 [00:01<00:00, 76296.43KB/s]
     68%|######8   | 90468/132723 [00:01<00:00, 76063.71KB/s]
     74%|#######3  | 98076/132723 [00:01<00:00, 76065.03KB/s]
     80%|#######9  | 105683/132723 [00:01<00:00, 75780.31KB/s]
     85%|########5 | 113262/132723 [00:01<00:00, 75679.69KB/s]
     91%|#########
 1| 120870/132723 [00:01<00:00, 75798.40KB/s]
     97%|#########6| 128450/132723 [00:01<00:00, 75732.44KB/s]
    100%|##########| 132723/132723 [00:01<00:00, 75299.00KB/s]
+
      0%|          | 0/132723 [00:00<?, ?KB/s]
      4%|4         | 5600/132723 [00:00<00:02, 55993.78KB/s]
     10%|9         | 13223/132723 [00:00<00:01, 67889.32KB/s]
     16%|#5        | 21134/132723 [00:00<00:01, 73011.08KB/s]
     22%|##1       | 29081/132723 [00:00<00:01, 75554.60KB/s]
     28%|##7       | 37066/132723 [00:00<00:01, 77102.04KB/s]
     34%|###3      | 45115/132723 [00:00<00:01, 78252.43KB/s]
     40%|####      | 53116/132723 [00:00<00:01, 78823.45KB/s]
     46%|####6     | 61104/132723 [00:00<00:00, 79157.94KB/s]
     52%|#####2    | 69172/132723 [00:00<00:00, 79626.51KB/s]
     58%|#####8    | 77257/132723 [00:01<00:00, 80000.50KB/s]
     64%|######4   | 85258/132723 [00:01<00:00, 79972.62KB/s]
     70%|#######   | 93267/132723 [00:01<00:00, 80005.91KB/s]
     76%|#######6  | 101310/132723 [00:01<00:00, 80132.81KB/s]
     82%|########2 | 109347/132723 [00:01<00:00, 80202.26KB/s]
     88%|########8 | 117404/132723 [00:01<00:00, 80303.48KB/s]
     95%|########
 #4| 125435/132723 [00:01<00:00, 80285.59KB/s]
    100%|##########| 132723/132723 [00:01<00:00, 78489.29KB/s]
 
 
 
@@ -246,7 +246,7 @@ Display result
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 3 minutes  11.812 seconds)
+   **Total running time of the script:** ( 3 minutes  4.930 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 8e1d596522..7f6f241058 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
 
 Computation times
 =================
-**13:57.688** total execution time for **how_to_deploy_models** files:
+**13:29.805** total execution time for **how_to_deploy_models** files:
 
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:23.678 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:15.612 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)                           | 03:11.812 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)                           | 03:04.930 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)           | 02:23.611 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)           | 02:21.747 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)                               | 01:30.417 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)                               | 01:26.011 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)                         | 01:08.878 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)                         | 01:05.543 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``)                   | 00:52.079 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``)                   | 00:51.212 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)                 | 00:36.392 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)                 | 00:35.522 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``)                       | 00:25.582 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``)                       | 00:24.829 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)                       | 00:25.231 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)                       | 00:24.394 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``)                                     | 00:00.007 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
index 5d2eea479b..054cfbbbe4 100644
--- a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
@@ -476,7 +476,7 @@ First let us define two helper functions to get the mobilenet model and a cat im
 
  .. code-block:: none
 
-    Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip59ffb2db-5533-40ad-899b-c7b06d7441b0 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+    Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip8393d624-278c-4db7-9a96-9cd1da431001 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 15b546b527..6f8b524283 100644
--- a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
 
 Computation times
 =================
-**00:48.786** total execution time for **how_to_extend_tvm** files:
+**00:46.995** total execution time for **how_to_extend_tvm** files:
 
 +-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:45.229 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:43.551 | 0.0 MB |
 +-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)           | 00:02.492 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)           | 00:02.410 | 0.0 MB |
 +-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)                     | 00:01.058 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)                     | 00:01.027 | 0.0 MB |
 +-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``)       | 00:00.008 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``)       | 00:00.007 | 0.0 MB |
 +-------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
index f621285b4a..e40e59eb64 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
@@ -220,10 +220,10 @@ profile the execution time of each passes.
  .. code-block:: none
 
     Printing results of timing profile...
-    InferType: 7301us [7301us] (46.40%; 46.40%)
-    FoldScaleAxis: 8434us [7us] (53.60%; 53.60%)
-            FoldConstant: 8427us [1744us] (53.56%; 99.91%)
-                    InferType: 6684us [6684us] (42.48%; 79.31%)
+    InferType: 7217us [7217us] (46.46%; 46.46%)
+    FoldScaleAxis: 8316us [7us] (53.54%; 53.54%)
+            FoldConstant: 8309us [1694us] (53.49%; 99.92%)
+                    InferType: 6616us [6616us] (42.59%; 79.62%)
 
 
 
@@ -262,10 +262,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
  .. code-block:: none
 
     Printing results of timing profile...
-    InferType: 6879us [6879us] (44.97%; 44.97%)
-    FoldScaleAxis: 8420us [6us] (55.03%; 55.03%)
-            FoldConstant: 8414us [1739us] (55.00%; 99.93%)
-                    InferType: 6675us [6675us] (43.63%; 79.33%)
+    InferType: 6672us [6672us] (44.96%; 44.96%)
+    FoldScaleAxis: 8167us [5us] (55.04%; 55.04%)
+            FoldConstant: 8161us [1681us] (55.00%; 99.93%)
+                    InferType: 6480us [6480us] (43.67%; 79.40%)
 
 
 
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 49fce0c40f..abcdebc1c4 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
@@ -344,7 +344,7 @@ latency of convolution.
 
  .. code-block:: none
 
-    Convolution: 54.184448 ms
+    Convolution: 49.154689 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 f545022375..a96b8a4397 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
@@ -661,7 +661,7 @@ be able to run on our build server
 
  .. code-block:: none
 
-    conv2d with tensor core: 13.364944 ms
+    conv2d with tensor core: 13.375894 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 f6564ad586..23951bbcd2 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -147,8 +147,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
 
  .. code-block:: none
 
-    Numpy running time: 0.019091
-    Baseline: 3.401195
+    Numpy running time: 0.018804
+    Baseline: 3.333080
 
 
 
@@ -242,7 +242,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
 
  .. code-block:: none
 
-    Opt1: 0.324664
+    Opt1: 0.300575
 
 
 
@@ -344,7 +344,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
 
  .. code-block:: none
 
-    Opt2: 0.352036
+    Opt2: 0.337051
 
 
 
@@ -439,7 +439,7 @@ the access pattern for A matrix is more cache friendly.
 
  .. code-block:: none
 
-    Opt3: 0.115808
+    Opt3: 0.116211
 
 
 
@@ -563,7 +563,7 @@ flattening.
 
  .. code-block:: none
 
-    Opt4: 0.107859
+    Opt4: 0.109564
 
 
 
@@ -684,7 +684,7 @@ write to C when all the block results are ready.
 
  .. code-block:: none
 
-    Opt5: 0.110809
+    Opt5: 0.111722
 
 
 
@@ -808,7 +808,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
 
  .. code-block:: none
 
-    Opt6: 0.146935
+    Opt6: 0.146651
 
 
 
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 0fabd19bac..aad3d349e8 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
 
 Computation times
 =================
-**00:35.389** total execution time for **how_to_optimize_operators** files:
+**00:34.657** total execution time for **how_to_optimize_operators** files:
 
 +-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)                       | 00:32.796 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)                       | 00:32.090 | 0.0 MB |
 +-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.527 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.501 | 0.0 MB |
 +-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)             | 00:01.067 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)             | 00:01.066 | 0.0 MB |
 +-----------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
index c1557bbf1d..8c0e955524 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
 
 Computation times
 =================
-**09:06.359** total execution time for **how_to_tune_with_autoscheduler** files:
+**09:04.667** total execution time for **how_to_tune_with_autoscheduler** files:
 
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:37.180 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:30.463 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)             | 01:33.553 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)             | 01:31.322 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)           | 01:02.636 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)           | 01:01.554 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)               | 00:28.895 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)               | 00:38.278 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)             | 00:12.633 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)             | 00:11.980 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)           | 00:11.461 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)           | 00:11.069 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
index 9bbbbfd055..54745f9820 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
@@ -243,11 +243,11 @@ cooperative fetching, unrolling and operator fusion.
                  bias: Buffer(bias_2: Pointer(float32), float32, [1, 512, 1, 1], []),
                  compute: Buffer(compute_2: Pointer(float32), float32, [1, 512, 7, 7], [])}
       buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute} {
-      attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 28;
+      attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 8;
       allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
-      allocate(pad_temp.shared: Pointer(shared float32), float32, [72]), storage_scope = shared;
-      allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
-      attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
+      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 {
         conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
         conv2d_nchw_1[1] = 0f32
         conv2d_nchw_1[2] = 0f32
@@ -263,462 +263,1071 @@ cooperative fetching, unrolling and operator fusion.
         conv2d_nchw_1[12] = 0f32
         conv2d_nchw_1[13] = 0f32
         for (rc.outer.outer: int32, 0, 64) {
-          for (ry.outer.outer: int32, 0, 3) {
-            let cse_var_2: int32 = (rc.outer.outer*72)
-            let cse_var_1: int32 = (ry.outer.outer*3)
-             {
-              attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
-                if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
-                  pad_temp.shared_1: Buffer(pad_temp.shared, float32, [72], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data_3: Buffer(data_2, float32, [25088], [])[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*4), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + fl [...]
-                }
-                if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
-                  pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data_3[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 1), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0f32, dtype=float32)
-                }
-                if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
-                  pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data_3[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 2), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0f32, dtype=float32)
-                }
-                if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
-                  pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data_3[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 3), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0f32, dtype=float32)
-                }
-              }
-              attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 64)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 64), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 128)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 128), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 192)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 256)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 256), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 320)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 320), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 384)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 448)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 448), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 512)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 512), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 576)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 640)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 640), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 704)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 704), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 768)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 147456)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 832)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 832), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 896)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 896), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 960)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 184320)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1024), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1088), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 221184)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1216), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1280), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1408), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1472), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 294912)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1600), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1664), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 331776)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1792), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1856), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 368640)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1984), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2048), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 405504)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2176), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2240), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 442368)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2368), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2432), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 479232)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2560), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2624), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 516096)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2752), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2816), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 552960)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2944), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3008), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*48)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*48)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*48)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*48)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*48)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*48)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*48)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+          let cse_var_1: int32 = (rc.outer.outer*72)
+           {
+            attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+            if @tir.likely((threadIdx.x_1 < 216), dtype=bool) {
+              pad_temp.shared_1: Buffer(pad_temp.shared, float32, [648], [], scope="shared")[(threadIdx.x_1*3)] = @tir.if_then_else((((3 <= floormod(threadIdx.x_1, 27)) && (floormod(threadIdx.x_1, 27) < 24)) && (0 < floormod(threadIdx.x_1, 3))), data_3: Buffer(data_2, float32, [25088], [])[(((((rc.outer.outer*392) + (floordiv(threadIdx.x_1, 27)*49)) + (floordiv(floormod(threadIdx.x_1, 27), 3)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 8)], 0f32, dtype=float32)
+              pad_temp.shared_1[((threadIdx.x_1*3) + 1)] = @tir.if_then_else(((3 <= floormod(threadIdx.x_1, 27)) && (floormod(threadIdx.x_1, 27) < 24)), data_3[(((((rc.outer.outer*392) + (floordiv(threadIdx.x_1, 27)*49)) + (floordiv(floormod(threadIdx.x_1, 27), 3)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 7)], 0f32, dtype=float32)
+              pad_temp.shared_1[((threadIdx.x_1*3) + 2)] = @tir.if_then_else((((3 <= floormod(threadIdx.x_1, 27)) && (floormod(threadIdx.x_1, 27) < 24)) && (floormod(threadIdx.x_1, 3) < 2)), data_3[(((((rc.outer.outer*392) + (floordiv(threadIdx.x_1, 27)*49)) + (floordiv(floormod(threadIdx.x_1, 27), 3)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 6)], 0f32, dtype=float32)
             }
+            attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+            kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[((((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_3[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 224), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+            kernel.shared_1[(threadIdx.x_2 + 448)] = kernel_3[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 448), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+            kernel.shared_1[(threadIdx.x_2 + 672)] = kernel_3[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 672), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+            kernel.shared_1[(threadIdx.x_2 + 896)] = kernel_3[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 896), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+            kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel_3[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1120), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+            kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel_3[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1344), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+            kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel_3[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1568), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+            kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel_3[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1792), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+            kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel_3[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 72)*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_3[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2240), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+            kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel_3[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2464), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+            kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel_3[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2688), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+            kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel_3[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2912), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+            kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel_3[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 3136), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+            kernel.shared_1[(threadIdx.x_2 + 3360)] = kernel_3[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 3360), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+            kernel.shared_1[(threadIdx.x_2 + 3584)] = kernel_3[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 3584), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+            kernel.shared_1[(threadIdx.x_2 + 3808)] = kernel_3[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 3808), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+            kernel.shared_1[(threadIdx.x_2 + 4032)] = kernel_3[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 72)*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_3[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 4256), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+            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_3[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 4480), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+            }
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*9)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*144)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*144)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*144)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*144)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*144)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*144)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*144)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 1)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 1)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 1)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 1)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 1)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 1)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 1)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 2)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 2)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 2)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 2)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 2)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 2)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 8)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 2)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 3)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 3)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 3)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 12)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 3)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 13)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 3)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 3)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 15)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 3)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 4)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 4)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 12)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 4)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 13)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 4)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 4)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 15)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 4)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 16)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 4)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 5)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 12)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 5)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 13)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 5)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 5)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 15)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 5)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 16)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 5)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 17)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 5)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 6)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 6)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 6)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 21)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 6)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 22)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 6)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 23)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 6)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 24)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 6)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 7)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 7)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 21)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 7)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 22)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 7)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 23)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 7)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 24)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 7)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 25)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 7)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 8)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 21)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 8)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 22)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 8)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 23)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 8)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 24)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 8)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 25)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 8)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 26)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 8)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 9)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 9)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 9)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 84)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 9)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 85)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 9)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 86)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 9)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 87)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 9)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 10)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 10)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 84)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 10)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 85)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 10)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 86)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 10)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 87)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 10)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 88)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 10)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 11)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 84)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 11)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 85)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 11)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 86)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 11)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 87)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 11)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 88)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 11)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 89)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 11)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 12)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 12)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 12)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 93)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 12)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 94)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 12)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 95)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 12)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 96)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 12)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 13)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 13)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 93)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 13)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 94)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 13)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 95)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 13)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 96)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 13)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 97)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 13)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 14)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 93)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 14)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 94)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 14)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 95)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 14)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 96)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 14)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 97)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 14)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 14)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 15)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 15)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 15)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 15)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 15)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 15)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 105)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 15)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 16)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 16)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 16)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 16)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 16)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 105)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 16)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 106)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 16)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 17)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 17)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 17)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 17)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 105)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 17)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 106)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 17)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 107)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 17)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 18)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 18)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 18)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 165)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 18)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 166)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 18)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 167)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 18)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 168)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 18)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 19)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 19)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 165)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 19)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 166)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 19)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 167)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 19)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 168)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 19)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 169)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 19)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 20)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 165)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 20)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 166)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 20)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 167)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 20)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 168)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 20)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 169)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 20)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 170)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 20)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 21)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 21)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 21)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 174)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 21)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 175)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 21)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 176)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 21)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 177)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 21)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 22)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 22)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 174)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 22)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 175)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 22)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 176)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 22)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 177)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 22)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 178)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 22)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 23)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 174)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 23)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 175)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 23)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 176)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 23)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 177)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 23)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 178)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 23)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 179)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 23)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 24)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 24)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 24)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 183)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 24)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 184)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 24)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 185)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 24)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 186)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 24)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 25)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 25)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 183)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 25)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 184)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 25)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 185)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 25)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 186)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 25)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 187)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 25)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 26)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 183)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 26)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 184)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 26)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 185)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 26)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 186)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 26)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 187)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 26)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 188)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 26)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 27)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 27)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 27)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 27)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 27)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 27)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 27)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 28)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 28)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 28)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 28)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 28)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 28)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 28)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 29)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 29)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 29)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 29)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 29)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 29)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 29)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 30)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 30)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 30)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 30)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 30)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 30)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 30)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 31)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 31)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 31)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 31)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 31)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 31)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 31)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 32)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 32)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 32)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 32)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 32)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 32)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 260)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 32)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 33)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 33)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 33)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 264)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 33)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 265)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 33)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 266)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 33)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 267)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 33)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 34)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 34)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 264)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 34)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 265)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 34)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 266)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 34)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 267)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 34)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 268)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 34)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 35)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 264)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 35)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 265)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 35)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 266)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 35)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 267)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 35)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 268)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 35)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 269)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 35)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 72)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 72)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 72)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 72)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 72)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 72)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 72)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 73)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 73)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 73)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 73)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 73)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 73)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 73)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 74)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 74)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 74)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 74)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 74)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 74)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 8)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 74)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 75)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 75)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 75)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 12)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 75)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 13)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 75)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 75)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 15)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 75)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 76)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 76)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 12)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 76)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 13)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 76)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 76)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 15)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 76)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 16)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 76)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 77)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 12)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 77)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 13)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 77)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 77)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 15)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 77)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 16)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 77)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 17)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 77)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 78)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 78)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 78)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 21)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 78)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 22)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 78)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 23)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 78)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 24)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 78)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 79)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 79)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 21)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 79)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 22)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 79)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 23)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 79)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 24)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 79)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 25)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 79)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 80)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 21)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 80)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 22)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 80)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 23)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 80)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 24)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 80)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 25)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 80)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 26)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 80)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 81)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 81)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 81)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 84)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 81)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 85)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 81)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 86)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 81)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 87)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 81)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 82)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 82)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 84)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 82)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 85)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 82)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 86)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 82)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 87)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 82)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 88)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 82)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 83)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 84)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 83)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 85)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 83)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 86)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 83)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 87)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 83)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 88)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 83)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 89)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 83)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 84)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 84)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 84)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 93)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 84)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 94)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 84)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 95)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 84)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 96)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 84)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 85)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 85)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 93)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 85)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 94)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 85)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 95)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 85)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 96)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 85)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 97)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 85)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 86)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 93)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 86)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 94)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 86)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 95)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 86)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 96)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 86)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 97)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 86)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 86)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 87)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 87)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 87)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 87)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 87)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 87)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 105)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 87)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 88)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 88)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 88)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 88)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 88)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 105)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 88)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 106)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 88)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 89)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 89)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 89)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 89)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 105)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 89)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 106)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 89)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 107)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 89)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 90)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 90)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 90)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 165)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 90)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 166)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 90)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 167)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 90)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 168)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 90)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 91)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 91)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 165)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 91)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 166)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 91)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 167)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 91)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 168)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 91)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 169)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 91)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 92)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 165)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 92)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 166)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 92)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 167)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 92)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 168)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 92)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 169)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 92)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 170)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 92)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 93)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 93)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 93)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 174)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 93)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 175)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 93)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 176)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 93)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 177)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 93)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 94)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 94)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 174)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 94)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 175)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 94)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 176)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 94)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 177)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 94)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 178)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 94)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 95)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 174)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 95)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 175)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 95)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 176)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 95)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 177)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 95)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 178)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 95)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 179)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 95)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 96)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 96)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 96)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 183)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 96)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 184)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 96)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 185)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 96)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 186)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 96)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 97)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 97)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 183)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 97)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 184)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 97)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 185)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 97)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 186)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 97)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 187)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 97)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 98)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 183)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 98)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 184)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 98)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 185)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 98)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 186)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 98)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 187)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 98)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 188)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 98)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 99)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 99)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 99)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 99)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 99)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 99)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 99)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 100)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 100)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 100)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 100)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 100)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 100)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 100)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 101)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 101)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 101)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 101)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 101)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 101)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 101)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 102)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 102)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 102)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 102)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 102)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 102)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 102)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 103)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 103)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 103)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 103)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 103)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 103)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 103)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 104)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 104)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 104)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 104)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 104)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 104)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 260)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 104)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 105)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 105)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 105)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 264)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 105)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 265)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 105)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 266)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 105)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 267)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 105)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 106)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 106)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 264)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 106)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 265)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 106)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 266)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 106)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 267)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 106)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 268)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 106)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 107)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 264)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 107)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 265)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 107)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 266)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 107)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 267)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 107)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 268)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 107)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 269)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 107)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 324)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 36)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 36)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 36)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 327)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 36)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 328)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 36)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 329)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 36)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 330)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 36)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 37)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 37)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 327)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 37)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 328)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 37)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 329)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 37)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 330)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 37)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 331)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 37)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 38)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 327)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 38)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 328)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 38)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 329)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 38)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 330)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 38)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 331)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 38)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 332)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 38)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 39)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 39)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 39)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 336)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 39)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 337)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 39)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 338)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 39)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 339)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 39)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 40)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 40)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 336)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 40)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 337)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 40)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 338)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 40)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 339)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 40)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 340)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 40)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 41)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 336)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 41)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 337)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 41)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 338)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 41)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 339)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 41)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 340)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 41)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 341)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 41)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 42)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 42)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 42)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 42)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 42)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 42)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 42)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 43)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 43)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 43)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 43)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 43)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 43)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 43)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 44)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 44)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 44)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 44)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 44)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 44)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 350)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 44)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 405)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 45)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 406)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 45)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 45)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 408)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 45)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 409)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 45)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 410)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 45)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 411)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 45)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 406)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 46)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 46)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 408)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 46)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 409)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 46)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 410)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 46)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 411)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 46)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 412)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 46)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 47)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 408)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 47)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 409)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 47)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 410)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 47)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 411)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 47)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 412)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 47)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 413)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 47)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 414)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 48)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 48)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 48)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 417)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 48)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 418)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 48)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 419)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 48)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 420)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 48)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 49)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 49)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 417)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 49)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 418)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 49)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 419)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 49)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 420)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 49)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 421)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 49)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 50)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 417)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 50)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 418)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 50)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 419)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 50)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 420)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 50)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 421)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 50)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 422)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 50)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 51)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 51)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 51)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 426)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 51)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 427)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 51)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 428)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 51)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 429)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 51)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 52)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 52)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 426)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 52)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 427)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 52)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 428)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 52)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 429)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 52)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 430)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 52)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 53)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 426)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 53)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 427)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 53)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 428)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 53)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 429)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 53)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 430)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 53)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 431)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 53)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 486)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 54)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 487)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 54)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 54)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 489)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 54)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 54)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 491)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 54)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 492)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 54)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 487)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 55)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 55)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 489)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 55)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 55)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 491)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 55)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 492)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 55)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 493)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 55)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 56)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 489)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 56)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 56)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 491)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 56)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 492)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 56)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 493)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 56)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 494)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 56)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 495)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 57)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 57)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 57)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 498)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 57)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 499)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 57)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 500)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 57)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 501)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 57)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 58)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 58)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 498)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 58)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 499)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 58)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 500)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 58)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 501)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 58)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 502)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 58)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 59)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 498)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 59)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 499)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 59)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 500)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 59)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 501)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 59)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 502)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 59)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 503)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 59)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 60)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 60)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 60)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 507)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 60)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 508)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 60)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 509)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 60)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 510)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 60)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 61)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 61)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 507)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 61)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 508)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 61)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 509)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 61)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 510)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 61)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 511)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 61)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 62)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 507)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 62)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 508)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 62)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 509)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 62)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 510)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 62)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 511)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 62)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 512)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 62)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 63)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 63)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 63)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 570)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 63)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 571)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 63)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 572)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 63)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 573)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 63)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 64)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 64)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 570)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 64)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 571)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 64)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 572)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 64)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 573)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 64)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 574)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 64)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 65)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 570)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 65)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 571)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 65)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 572)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 65)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 573)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 65)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 574)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 65)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 575)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 65)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 66)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 66)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 66)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 579)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 66)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 580)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 66)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 581)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 66)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 582)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 66)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 67)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 67)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 579)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 67)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 580)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 67)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 581)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 67)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 582)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 67)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 583)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 67)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 68)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 579)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 68)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 580)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 68)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 581)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 68)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 582)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 68)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 583)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 68)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 584)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 68)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 69)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 69)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 69)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 69)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 589)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 69)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 590)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 69)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 591)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 69)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 70)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 70)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 70)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 589)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 70)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 590)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 70)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 591)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 70)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 592)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 70)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 71)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 71)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 589)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 71)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 590)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 71)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 591)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 71)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 592)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 71)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 593)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 71)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 324)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 108)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 108)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 108)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 327)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 108)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 328)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 108)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 329)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 108)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 330)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 108)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 109)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 109)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 327)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 109)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 328)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 109)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 329)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 109)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 330)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 109)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 331)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 109)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 110)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 327)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 110)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 328)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 110)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 329)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 110)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 330)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 110)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 331)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 110)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 332)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 110)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 111)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 111)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 111)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 336)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 111)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 337)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 111)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 338)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 111)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 339)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 111)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 112)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 112)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 336)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 112)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 337)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 112)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 338)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 112)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 339)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 112)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 340)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 112)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 113)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 336)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 113)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 337)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 113)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 338)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 113)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 339)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 113)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 340)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 113)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 341)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 113)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 114)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 114)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 114)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 114)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 114)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 114)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 114)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 115)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 115)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 115)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 115)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 115)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 115)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 115)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 116)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 116)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 116)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 116)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 116)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 116)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 350)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 116)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 405)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 117)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 406)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 117)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 117)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 408)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 117)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 409)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 117)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 410)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 117)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 411)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 117)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 406)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 118)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 118)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 408)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 118)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 409)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 118)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 410)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 118)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 411)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 118)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 412)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 118)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 119)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 408)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 119)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 409)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 119)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 410)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 119)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 411)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 119)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 412)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 119)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 413)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 119)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 414)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 120)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 120)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 120)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 417)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 120)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 418)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 120)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 419)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 120)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 420)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 120)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 121)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 121)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 417)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 121)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 418)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 121)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 419)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 121)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 420)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 121)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 421)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 121)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 122)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 417)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 122)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 418)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 122)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 419)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 122)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 420)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 122)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 421)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 122)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 422)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 122)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 123)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 123)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 123)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 426)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 123)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 427)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 123)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 428)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 123)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 429)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 123)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 124)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 124)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 426)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 124)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 427)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 124)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 428)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 124)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 429)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 124)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 430)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 124)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 125)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 426)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 125)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 427)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 125)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 428)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 125)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 429)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 125)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 430)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 125)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 431)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 125)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 486)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 126)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 487)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 126)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 126)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 489)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 126)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 126)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 491)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 126)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 492)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 126)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 487)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 127)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 127)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 489)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 127)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 127)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 491)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 127)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 492)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 127)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 493)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 127)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 128)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 489)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 128)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 128)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 491)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 128)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 492)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 128)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 493)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 128)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 494)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 128)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 495)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 129)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 129)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 129)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 498)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 129)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 499)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 129)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 500)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 129)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 501)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 129)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 130)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 130)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 498)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 130)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 499)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 130)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 500)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 130)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 501)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 130)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 502)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 130)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 131)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 498)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 131)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 499)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 131)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 500)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 131)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 501)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 131)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 502)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 131)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 503)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 131)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 132)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 132)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 132)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 507)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 132)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 508)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 132)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 509)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 132)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 510)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 132)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 133)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 133)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 507)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 133)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 508)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 133)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 509)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 133)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 510)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 133)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 511)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 133)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 134)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 507)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 134)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 508)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 134)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 509)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 134)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 510)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 134)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 511)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 134)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 512)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 134)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 135)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 135)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 135)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 570)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 135)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 571)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 135)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 572)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 135)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 573)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 135)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 136)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 136)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 570)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 136)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 571)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 136)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 572)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 136)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 573)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 136)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 574)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 136)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 137)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 570)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 137)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 571)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 137)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 572)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 137)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 573)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 137)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 574)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 137)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 575)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 137)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 138)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 138)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 138)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 579)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 138)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 580)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 138)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 581)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 138)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 582)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 138)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 139)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 139)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 579)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 139)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 580)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 139)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 581)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 139)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 582)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 139)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 583)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 139)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 140)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 579)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 140)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 580)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 140)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 581)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 140)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 582)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 140)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 583)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 140)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 584)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 140)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 141)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 141)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 141)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 141)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 589)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 141)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 590)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 141)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 591)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 141)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 142)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 142)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 142)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 589)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 142)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 590)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 142)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 591)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 142)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 592)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 142)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 143)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 143)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 589)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 143)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 590)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 143)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 591)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 143)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 592)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 143)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 593)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 143)]))
           }
         }
         for (i1.inner: int32, 0, 2) {
           for (i3.inner: int32, 0, 7) {
-            compute_3: Buffer(compute_2, float32, [25088], [])[(((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias_3: Buffer(bias_2, float32, [512], [])[(((floordiv(blockIdx.x, 7)*128) + (threadIdx.x*2)) + i1.inner)]), 0f32)
+            compute_3: Buffer(compute_2, float32, [25088], [])[(((((blockIdx.x*3136) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias_3: Buffer(bias_2, float32, [512], [])[(((blockIdx.x*64) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
           }
         }
       }
@@ -774,7 +1383,7 @@ We build the binary and check its correctness and performance.
 
  .. code-block:: none
 
-    Execution time of this operator: 0.366 ms
+    Execution time of this operator: 0.275 ms
 
 
 
@@ -824,31 +1433,31 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
     conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
     conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
     conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
-    conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
+    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=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_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
     conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
-    conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
-    conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
+    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=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=1)
+    conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
+    conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
+    conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
     conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
-    conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=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)
     compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
     compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
-    compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
+    compute_i1_o_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=1)
-    compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+    compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
     compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
     compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
     compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
@@ -871,14 +1480,14 @@ 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=64)
+    kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=224)
     s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
     pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
-    pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=4)
+    pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=3)
     s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-    pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
+    pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=224)
     s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
-    s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
+    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:
@@ -896,10 +1505,10 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
       #define int64_t long long
       #define uint64_t unsigned long long
     #endif
-    extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+    extern "C" __global__ void __launch_bounds__(224) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
       float conv2d_nchw[14];
-      __shared__ float pad_temp_shared[72];
-      __shared__ float kernel_shared[3072];
+      __shared__ float pad_temp_shared[648];
+      __shared__ float kernel_shared[4608];
       conv2d_nchw[0] = 0.000000e+00f;
       conv2d_nchw[1] = 0.000000e+00f;
       conv2d_nchw[2] = 0.000000e+00f;
@@ -915,410 +1524,1048 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
       conv2d_nchw[12] = 0.000000e+00f;
       conv2d_nchw[13] = 0.000000e+00f;
       for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
-        for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
-          __syncthreads();
-          if (((int)threadIdx.x) < 18) {
-            pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
-          }
-          if (((int)threadIdx.x) < 18) {
-            pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
-          }
-          if (((int)threadIdx.x) < 18) {
-            pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
-          }
-          if (((int)threadIdx.x) < 18) {
-            pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
-          }
-          kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
-          kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
-          kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
-          kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
-          kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
-          kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
-          kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
-          kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
-          kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
-          kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
-          kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
-          kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
-          kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
-          kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
-          kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
-          kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          __syncthreads();
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 48)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 48)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 48)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 48)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 48)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 48)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 48)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+        __syncthreads();
+        if (((int)threadIdx.x) < 216) {
+          pad_temp_shared[(((int)threadIdx.x) * 3)] = ((((3 <= (((int)threadIdx.x) % 27)) && ((((int)threadIdx.x) % 27) < 24)) && (0 < (((int)threadIdx.x) % 3))) ? data[(((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 27) * 49)) + (((((int)threadIdx.x) % 27) / 3) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 8)] : 0.000000e+00f);
+          pad_temp_shared[((((int)threadIdx.x) * 3) + 1)] = (((3 <= (((int)threadIdx.x) % 27)) && ((((int)threadIdx.x) % 27) < 24)) ? data[(((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 27) * 49)) + (((((int)threadIdx.x) % 27) / 3) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 7)] : 0.000000e+00f);
+          pad_temp_shared[((((int)threadIdx.x) * 3) + 2)] = ((((3 <= (((int)threadIdx.x) % 27)) && ((((int)threadIdx.x) % 27) < 24)) && ((((int)threadIdx.x) % 3) < 2)) ? data[(((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 27) * 49)) + (((((int)threadIdx.x) % 27) / 3) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 6)] : 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) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+        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) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+        kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 672) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+        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) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+        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) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+        kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1344) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+        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) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+        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) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+        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) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+        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) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+        kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2688) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+        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) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+        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) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+        kernel_shared[(((int)threadIdx.x) + 3360)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3360) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+        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) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+        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) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+        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) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+        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) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
         }
+        __syncthreads();
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 9)] * kernel_shared[((((int)threadIdx.x) / 7) * 144)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[((((int)threadIdx.x) / 7) * 144)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[((((int)threadIdx.x) / 7) * 144)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[((((int)threadIdx.x) / 7) * 144)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[((((int)threadIdx.x) / 7) * 144)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[((((int)threadIdx.x) / 7) * 144)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[((((int)threadIdx.x) / 7) * 144)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 1)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 1)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 1)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 1)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 1)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 1)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 1)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 2)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 2)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 2)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 2)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 2)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 2)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 8)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 2)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 3)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 3)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 3)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 3)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 3)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 3)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 3)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 4)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 4)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 4)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 4)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 4)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 4)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 16)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 4)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 5)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 5)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 5)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 5)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 5)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 16)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 5)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 17)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 5)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 6)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 6)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 6)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 6)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 6)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 6)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 24)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 6)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 7)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 7)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 7)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 7)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 7)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 24)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 7)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 25)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 7)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 8)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 8)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 8)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 8)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 24)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 8)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 25)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 8)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 26)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 8)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 9)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 9)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 9)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 9)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 9)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 9)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 9)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 10)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 10)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 10)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 10)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 10)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 10)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 88)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 10)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 11)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 11)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 11)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 11)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 11)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 88)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 11)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 89)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 11)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 12)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 12)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 12)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 93)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 12)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 94)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 12)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 95)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 12)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 96)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 12)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 13)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 13)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 93)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 13)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 94)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 13)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 95)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 13)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 96)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 13)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 97)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 13)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 14)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 93)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 14)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 94)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 14)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 95)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 14)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 96)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 14)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 97)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 14)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 14)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 15)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 15)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 15)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 15)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 15)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 15)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 105)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 15)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 16)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 16)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 16)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 16)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 16)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 105)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 16)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 106)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 16)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 17)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 17)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 17)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 17)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 105)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 17)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 106)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 17)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 107)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 17)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 162)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 18)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 163)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 18)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 18)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 165)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 18)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 166)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 18)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 167)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 18)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 168)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 18)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 163)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 19)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 19)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 165)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 19)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 166)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 19)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 167)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 19)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 168)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 19)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 169)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 19)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 20)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 165)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 20)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 166)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 20)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 167)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 20)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 168)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 20)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 169)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 20)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 170)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 20)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 171)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 21)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 21)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 21)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 174)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 21)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 175)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 21)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 176)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 21)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 177)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 21)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 22)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 22)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 174)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 22)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 175)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 22)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 176)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 22)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 177)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 22)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 178)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 22)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 23)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 174)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 23)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 175)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 23)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 176)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 23)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 177)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 23)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 178)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 23)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 179)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 23)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 24)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 24)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 24)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 183)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 24)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 184)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 24)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 185)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 24)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 186)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 24)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 25)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 25)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 183)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 25)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 184)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 25)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 185)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 25)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 186)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 25)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 187)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 25)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 26)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 183)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 26)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 184)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 26)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 185)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 26)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 186)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 26)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 187)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 26)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 188)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 26)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 243)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 27)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 244)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 27)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 27)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 27)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 27)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 27)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 27)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 244)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 28)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 28)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 28)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 28)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 28)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 28)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 28)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 29)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 29)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 29)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 29)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 29)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 29)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 29)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 30)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 30)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 30)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 30)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 30)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 30)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 30)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 31)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 31)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 31)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 31)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 31)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 31)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 31)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 32)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 32)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 32)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 32)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 32)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 32)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 260)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 32)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 33)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 33)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 33)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 264)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 33)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 265)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 33)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 266)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 33)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 267)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 33)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 34)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 34)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 264)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 34)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 265)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 34)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 266)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 34)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 267)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 34)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 268)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 34)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 35)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 264)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 35)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 265)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 35)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 266)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 35)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 267)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 35)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 268)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 35)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 269)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 35)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 72)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 72)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 72)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 72)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 72)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 72)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 72)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 73)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 73)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 73)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 73)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 73)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 73)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 73)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 74)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 74)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 74)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 74)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 74)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 74)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 8)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 74)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 75)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 75)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 75)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 75)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 75)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 75)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 75)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 76)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 76)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 76)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 76)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 76)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 76)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 16)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 76)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 77)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 77)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 77)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 77)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 77)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 16)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 77)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 17)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 77)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 78)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 78)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 78)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 78)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 78)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 78)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 24)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 78)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 79)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 79)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 79)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 79)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 79)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 24)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 79)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 25)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 79)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 80)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 80)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 80)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 80)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 24)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 80)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 25)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 80)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 26)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 80)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 81)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 81)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 81)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 81)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 81)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 81)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 81)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 82)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 82)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 82)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 82)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 82)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 82)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 88)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 82)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 83)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 83)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 83)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 83)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 83)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 88)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 83)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 89)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 83)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 84)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 84)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 84)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 93)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 84)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 94)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 84)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 95)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 84)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 96)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 84)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 85)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 85)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 93)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 85)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 94)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 85)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 95)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 85)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 96)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 85)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 97)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 85)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 86)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 93)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 86)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 94)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 86)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 95)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 86)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 96)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 86)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 97)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 86)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 86)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 87)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 87)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 87)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 87)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 87)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 87)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 105)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 87)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 88)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 88)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 88)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 88)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 88)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 105)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 88)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 106)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 88)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 89)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 89)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 89)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 89)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 105)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 89)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 106)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 89)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 107)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 89)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 162)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 90)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 163)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 90)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 90)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 165)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 90)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 166)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 90)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 167)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 90)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 168)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 90)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 163)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 91)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 91)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 165)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 91)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 166)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 91)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 167)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 91)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 168)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 91)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 169)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 91)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 92)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 165)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 92)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 166)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 92)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 167)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 92)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 168)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 92)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 169)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 92)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 170)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 92)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 171)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 93)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 93)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 93)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 174)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 93)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 175)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 93)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 176)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 93)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 177)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 93)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 94)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 94)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 174)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 94)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 175)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 94)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 176)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 94)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 177)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 94)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 178)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 94)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 95)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 174)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 95)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 175)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 95)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 176)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 95)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 177)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 95)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 178)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 95)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 179)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 95)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 96)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 96)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 96)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 183)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 96)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 184)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 96)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 185)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 96)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 186)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 96)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 97)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 97)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 183)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 97)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 184)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 97)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 185)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 97)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 186)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 97)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 187)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 97)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 98)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 183)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 98)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 184)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 98)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 185)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 98)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 186)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 98)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 187)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 98)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 188)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 98)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 243)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 99)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 244)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 99)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 99)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 99)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 99)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 99)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 99)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 244)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 100)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 100)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 100)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 100)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 100)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 100)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 100)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 101)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 101)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 101)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 101)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 101)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 101)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 101)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 102)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 102)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 102)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 102)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 102)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 102)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 102)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 103)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 103)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 103)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 103)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 103)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 103)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 103)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 104)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 104)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 104)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 104)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 104)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 104)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 260)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 104)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 105)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 105)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 105)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 264)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 105)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 265)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 105)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 266)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 105)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 267)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 105)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 106)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 106)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 264)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 106)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 265)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 106)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 266)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 106)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 267)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 106)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 268)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 106)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 107)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 264)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 107)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 265)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 107)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 266)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 107)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 267)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 107)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 268)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 107)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 269)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 107)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 324)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 36)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 325)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 36)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 326)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 36)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 327)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 36)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 328)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 36)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 329)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 36)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 330)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 36)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 325)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 37)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 326)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 37)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 327)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 37)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 328)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 37)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 329)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 37)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 330)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 37)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 331)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 37)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 326)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 38)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 327)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 38)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 328)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 38)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 329)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 38)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 330)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 38)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 331)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 38)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 332)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 38)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 333)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 39)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 334)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 39)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 335)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 39)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 336)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 39)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 337)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 39)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 338)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 39)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 339)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 39)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 334)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 40)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 335)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 40)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 336)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 40)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 337)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 40)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 338)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 40)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 339)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 40)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 340)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 40)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 335)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 41)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 336)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 41)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 337)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 41)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 338)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 41)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 339)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 41)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 340)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 41)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 341)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 41)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 342)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 42)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 42)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 42)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 42)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 42)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 42)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 42)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 43)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 43)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 43)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 43)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 43)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 43)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 43)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 44)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 44)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 44)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 44)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 44)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 44)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 350)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 44)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 405)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 45)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 406)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 45)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 407)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 45)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 408)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 45)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 409)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 45)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 410)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 45)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 411)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 45)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 406)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 46)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 407)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 46)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 408)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 46)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 409)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 46)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 410)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 46)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 411)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 46)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 412)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 46)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 407)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 47)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 408)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 47)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 409)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 47)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 410)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 47)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 411)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 47)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 412)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 47)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 413)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 47)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 414)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 48)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 415)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 48)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 416)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 48)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 417)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 48)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 418)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 48)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 419)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 48)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 420)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 48)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 415)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 49)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 416)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 49)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 417)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 49)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 418)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 49)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 419)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 49)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 420)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 49)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 421)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 49)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 416)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 50)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 417)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 50)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 418)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 50)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 419)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 50)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 420)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 50)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 421)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 50)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 422)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 50)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 423)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 51)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 424)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 51)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 425)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 51)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 426)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 51)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 427)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 51)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 428)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 51)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 429)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 51)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 424)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 52)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 425)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 52)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 426)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 52)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 427)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 52)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 428)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 52)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 429)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 52)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 430)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 52)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 425)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 53)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 426)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 53)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 427)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 53)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 428)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 53)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 429)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 53)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 430)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 53)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 431)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 53)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 486)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 54)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 487)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 54)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 488)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 54)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 489)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 54)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 490)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 54)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 491)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 54)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 492)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 54)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 487)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 55)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 488)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 55)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 489)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 55)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 490)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 55)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 491)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 55)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 492)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 55)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 493)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 55)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 488)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 56)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 489)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 56)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 490)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 56)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 491)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 56)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 492)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 56)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 493)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 56)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 494)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 56)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 495)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 57)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 496)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 57)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 497)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 57)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 498)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 57)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 499)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 57)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 500)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 57)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 501)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 57)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 496)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 58)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 497)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 58)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 498)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 58)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 499)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 58)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 500)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 58)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 501)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 58)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 502)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 58)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 497)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 59)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 498)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 59)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 499)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 59)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 500)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 59)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 501)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 59)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 502)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 59)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 503)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 59)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 504)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 60)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 505)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 60)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 60)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 507)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 60)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 508)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 60)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 509)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 60)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 510)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 60)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 505)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 61)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 61)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 507)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 61)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 508)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 61)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 509)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 61)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 510)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 61)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 511)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 61)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 62)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 507)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 62)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 508)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 62)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 509)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 62)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 510)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 62)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 511)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 62)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 512)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 62)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 567)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 63)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 568)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 63)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 569)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 63)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 570)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 63)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 571)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 63)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 572)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 63)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 573)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 63)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 568)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 64)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 569)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 64)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 570)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 64)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 571)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 64)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 572)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 64)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 573)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 64)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 574)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 64)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 569)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 65)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 570)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 65)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 571)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 65)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 572)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 65)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 573)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 65)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 574)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 65)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 575)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 65)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 576)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 66)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 577)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 66)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 578)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 66)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 579)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 66)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 580)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 66)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 581)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 66)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 582)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 66)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 577)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 67)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 578)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 67)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 579)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 67)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 580)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 67)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 581)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 67)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 582)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 67)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 583)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 67)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 578)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 68)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 579)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 68)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 580)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 68)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 581)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 68)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 582)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 68)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 583)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 68)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 584)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 68)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 585)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 69)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 586)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 69)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 69)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 588)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 69)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 589)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 69)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 590)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 69)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 591)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 69)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 586)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 70)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 70)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 588)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 70)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 589)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 70)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 590)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 70)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 591)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 70)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 592)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 70)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 71)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 588)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 71)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 589)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 71)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 590)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 71)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 591)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 71)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 592)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 71)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 593)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 71)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 324)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 108)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 325)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 108)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 326)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 108)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 327)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 108)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 328)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 108)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 329)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 108)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 330)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 108)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 325)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 109)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 326)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 109)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 327)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 109)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 328)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 109)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 329)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 109)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 330)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 109)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 331)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 109)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 326)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 110)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 327)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 110)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 328)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 110)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 329)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 110)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 330)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 110)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 331)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 110)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 332)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 110)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 333)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 111)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 334)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 111)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 335)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 111)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 336)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 111)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 337)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 111)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 338)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 111)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 339)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 111)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 334)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 112)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 335)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 112)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 336)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 112)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 337)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 112)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 338)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 112)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 339)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 112)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 340)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 112)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 335)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 113)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 336)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 113)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 337)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 113)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 338)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 113)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 339)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 113)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 340)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 113)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 341)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 113)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 342)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 114)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 114)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 114)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 114)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 114)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 114)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 114)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 115)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 115)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 115)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 115)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 115)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 115)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 115)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 116)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 116)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 116)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 116)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 116)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 116)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 350)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 116)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 405)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 117)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 406)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 117)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 407)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 117)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 408)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 117)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 409)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 117)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 410)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 117)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 411)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 117)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 406)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 118)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 407)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 118)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 408)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 118)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 409)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 118)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 410)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 118)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 411)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 118)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 412)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 118)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 407)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 119)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 408)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 119)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 409)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 119)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 410)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 119)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 411)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 119)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 412)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 119)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 413)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 119)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 414)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 120)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 415)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 120)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 416)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 120)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 417)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 120)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 418)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 120)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 419)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 120)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 420)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 120)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 415)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 121)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 416)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 121)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 417)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 121)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 418)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 121)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 419)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 121)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 420)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 121)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 421)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 121)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 416)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 122)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 417)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 122)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 418)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 122)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 419)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 122)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 420)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 122)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 421)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 122)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 422)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 122)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 423)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 123)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 424)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 123)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 425)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 123)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 426)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 123)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 427)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 123)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 428)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 123)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 429)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 123)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 424)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 124)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 425)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 124)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 426)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 124)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 427)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 124)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 428)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 124)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 429)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 124)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 430)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 124)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 425)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 125)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 426)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 125)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 427)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 125)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 428)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 125)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 429)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 125)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 430)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 125)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 431)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 125)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 486)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 126)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 487)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 126)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 488)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 126)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 489)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 126)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 490)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 126)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 491)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 126)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 492)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 126)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 487)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 127)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 488)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 127)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 489)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 127)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 490)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 127)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 491)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 127)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 492)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 127)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 493)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 127)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 488)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 128)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 489)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 128)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 490)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 128)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 491)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 128)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 492)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 128)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 493)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 128)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 494)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 128)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 495)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 129)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 496)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 129)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 497)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 129)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 498)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 129)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 499)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 129)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 500)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 129)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 501)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 129)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 496)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 130)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 497)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 130)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 498)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 130)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 499)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 130)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 500)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 130)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 501)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 130)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 502)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 130)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 497)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 131)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 498)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 131)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 499)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 131)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 500)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 131)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 501)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 131)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 502)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 131)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 503)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 131)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 504)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 132)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 505)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 132)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 132)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 507)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 132)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 508)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 132)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 509)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 132)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 510)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 132)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 505)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 133)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 133)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 507)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 133)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 508)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 133)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 509)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 133)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 510)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 133)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 511)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 133)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 134)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 507)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 134)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 508)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 134)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 509)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 134)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 510)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 134)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 511)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 134)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 512)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 134)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 567)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 135)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 568)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 135)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 569)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 135)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 570)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 135)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 571)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 135)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 572)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 135)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 573)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 135)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 568)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 136)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 569)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 136)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 570)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 136)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 571)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 136)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 572)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 136)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 573)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 136)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 574)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 136)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 569)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 137)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 570)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 137)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 571)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 137)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 572)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 137)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 573)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 137)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 574)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 137)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 575)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 137)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 576)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 138)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 577)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 138)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 578)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 138)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 579)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 138)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 580)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 138)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 581)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 138)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 582)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 138)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 577)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 139)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 578)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 139)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 579)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 139)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 580)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 139)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 581)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 139)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 582)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 139)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 583)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 139)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 578)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 140)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 579)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 140)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 580)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 140)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 581)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 140)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 582)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 140)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 583)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 140)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 584)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 140)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 585)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 141)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 586)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 141)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 141)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 588)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 141)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 589)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 141)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 590)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 141)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 591)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 141)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 586)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 142)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 142)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 588)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 142)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 589)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 142)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 590)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 142)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 591)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 142)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 592)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 142)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 143)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 588)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 143)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 589)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 143)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 590)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 143)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 591)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 143)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 592)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 143)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 593)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 143)]));
       }
       for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
         for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
-          compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
+          compute[(((((((int)blockIdx.x) * 3136) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[(((((int)blockIdx.x) * 64) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
         }
       }
     }
@@ -1381,7 +2628,7 @@ In the example below we resume the status and do more 5 trials.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 5 minutes  37.180 seconds)
+   **Total running time of the script:** ( 5 minutes  30.463 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 b98f94bf29..42b3c1aff6 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -647,7 +647,7 @@ so we can read the log file and load the best schedules.
     Evaluate inference time cost...
     Execution time summary:
      mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)  
-       7.8641       7.8585       7.8794       7.8543       0.0110   
+       7.9025       7.9078       7.9138       7.8859       0.0120   
                
 
 
@@ -675,7 +675,7 @@ Other Tips
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  2.636 seconds)
+   **Total running time of the script:** ( 1 minutes  1.554 seconds)
 
 
 .. _sphx_glr_download_how_to_tune_with_autoscheduler_tune_network_cuda.py:
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
index c831604adf..16b3936625 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
@@ -666,7 +666,7 @@ so we can read the log file and load the best schedules.
     Evaluate inference time cost...
     Execution time summary:
      mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)  
-      764.2900     764.1682     765.1351     763.5668      0.6460   
+      748.4852     748.3161     748.9514     748.1880      0.3338   
                
 
 
@@ -694,7 +694,7 @@ Other Tips
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  33.553 seconds)
+   **Total running time of the script:** ( 1 minutes  31.322 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 230235ba09..99ff68789b 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
@@ -390,28 +390,80 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
                  placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [128, 512], []),
                  compute: Buffer(compute_2: Pointer(float32), float32, [128, 512], [])}
       buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute} {
-      allocate(compute_3: Pointer(global float32), float32, [2048]), storage_scope = global;
-      for (i1.outer: int32, 0, 32) {
-        for (i.outer.inner: int32, 0, 32) {
-          for (i.inner.init: int32, 0, 4) {
-            for (j.init: int32, 0, 16) {
-              compute_4: Buffer(compute_3, float32, [2048], [])[(((i.outer.inner*64) + (i.inner.init*16)) + j.init)] = 0f32
-            }
-          }
-          for (elem_idx: int32, 0, (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(i1.outer + 1)] - placeholder_15[i1.outer])) {
-            for (i.inner: int32, 0, 4) {
-              for (j: int32, 0, 16) {
-                if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
-                  let cse_var_1: int32 = (((i.outer.inner*64) + (i.inner*16)) + j)
-                  compute_4[cse_var_1] = (compute_4[cse_var_1] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + j)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[(((i.outer.inner*1024) + (i.inner*256)) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[i1.outer] + elem_idx)])], 0f32)))
+      for (i0.outer.i1.outer.fused: int32, 0, 16) "parallel" {
+        allocate(compute_3: Pointer(global float32), float32, [4096]), storage_scope = global {
+          for (i.outer.inner: int32, 0, 4) {
+            for (nb_j.inner: int32, 0, 2) {
+              for (i.inner.init: int32, 0, 32) {
+                let cse_var_1: int32 = (((i.outer.inner*1024) + (i.inner.init*32)) + (nb_j.inner*16))
+                 {
+                  compute_4: Buffer(compute_3, float32, [4096], [])[cse_var_1] = 0f32
+                  compute_4[(cse_var_1 + 1)] = 0f32
+                  compute_4[(cse_var_1 + 2)] = 0f32
+                  compute_4[(cse_var_1 + 3)] = 0f32
+                  compute_4[(cse_var_1 + 4)] = 0f32
+                  compute_4[(cse_var_1 + 5)] = 0f32
+                  compute_4[(cse_var_1 + 6)] = 0f32
+                  compute_4[(cse_var_1 + 7)] = 0f32
+                  compute_4[(cse_var_1 + 8)] = 0f32
+                  compute_4[(cse_var_1 + 9)] = 0f32
+                  compute_4[(cse_var_1 + 10)] = 0f32
+                  compute_4[(cse_var_1 + 11)] = 0f32
+                  compute_4[(cse_var_1 + 12)] = 0f32
+                  compute_4[(cse_var_1 + 13)] = 0f32
+                  compute_4[(cse_var_1 + 14)] = 0f32
+                  compute_4[(cse_var_1 + 15)] = 0f32
+                }
+              }
+              for (elem_idx: int32, 0, let cse_var_2: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_2 + 1)] - placeholder_15[cse_var_2])) {
+                for (i.inner: int32, 0, 32) {
+                  let cse_var_21: int32 = (elem_idx*16)
+                  let cse_var_20: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
+                  let cse_var_19: int32 = ((i.outer.inner*8192) + (i.inner*256))
+                  let cse_var_18: int32 = (((i.outer.inner*1024) + (i.inner*32)) + (nb_j.inner*16))
+                  let cse_var_17: int32 = (cse_var_18 + 9)
+                  let cse_var_16: int32 = (cse_var_18 + 8)
+                  let cse_var_15: int32 = (cse_var_18 + 7)
+                  let cse_var_14: int32 = (cse_var_18 + 6)
+                  let cse_var_13: int32 = (cse_var_18 + 5)
+                  let cse_var_12: int32 = (cse_var_18 + 4)
+                  let cse_var_11: int32 = (cse_var_18 + 3)
+                  let cse_var_10: int32 = (cse_var_18 + 2)
+                  let cse_var_9: int32 = (cse_var_18 + 15)
+                  let cse_var_8: int32 = (cse_var_18 + 14)
+                  let cse_var_7: int32 = (cse_var_18 + 13)
+                  let cse_var_6: int32 = (cse_var_18 + 12)
+                  let cse_var_5: int32 = (cse_var_18 + 11)
+                  let cse_var_4: int32 = (cse_var_18 + 10)
+                  let cse_var_3: int32 = (cse_var_18 + 1)
+                   {
+                    compute_4[cse_var_18] = (compute_4[cse_var_18] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[((placeholder_15[cse_var_20]*16) + cse_var_21)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[(cse_var_19 + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_4[cse_var_3] = (compute_4[cse_var_3] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_4[cse_var_10] = (compute_4[cse_var_10] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_4[cse_var_11] = (compute_4[cse_var_11] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_4[cse_var_12] = (compute_4[cse_var_12] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_4[cse_var_13] = (compute_4[cse_var_13] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_4[cse_var_14] = (compute_4[cse_var_14] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_4[cse_var_15] = (compute_4[cse_var_15] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_4[cse_var_16] = (compute_4[cse_var_16] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_4[cse_var_17] = (compute_4[cse_var_17] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_4[cse_var_4] = (compute_4[cse_var_4] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_4[cse_var_5] = (compute_4[cse_var_5] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_4[cse_var_6] = (compute_4[cse_var_6] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_4[cse_var_7] = (compute_4[cse_var_7] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_4[cse_var_8] = (compute_4[cse_var_8] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_4[cse_var_9] = (compute_4[cse_var_9] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                  }
                 }
               }
             }
           }
-        }
-        for (i0.inner: int32, 0, 128) {
-          let cse_var_2: int32 = ((i0.inner*512) + (i1.outer*16))
-          compute_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_2, 1, 16)] = max((compute_4[ramp((i0.inner*16), 1, 16)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_2, 1, 16)]), broadcast(0f32, 16))
+          for (i0.inner: int32, 0, 128) {
+            for (i1.inner: int32, 0, 32) {
+              let cse_var_22: int32 = (((i0.inner*512) + (i0.outer.i1.outer.fused*32)) + i1.inner)
+              compute_5: Buffer(compute_2, float32, [65536], [])[cse_var_22] = max((compute_4[((i0.inner*32) + i1.inner)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[cse_var_22]), 0f32)
+            }
+          }
         }
       }
     }
@@ -466,7 +518,7 @@ We build the binary and check its correctness and performance.
 
  .. code-block:: none
 
-    Execution time of this operator: 1.335 ms
+    Execution time of this operator: 1.727 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 0b61c26ed1..455ec34496 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
 
 Computation times
 =================
-**00:31.464** total execution time for **how_to_tune_with_autotvm** files:
+**00:55.139** total execution time for **how_to_tune_with_autotvm** files:
 
 +--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)           | 00:31.426 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)           | 00:55.103 | 0.0 MB |
 +--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)               | 00:00.022 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)               | 00:00.020 | 0.0 MB |
 +--------------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``)             | 00:00.005 | 0.0 MB |
 +--------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
index a412a3744d..6071f92cca 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
@@ -269,9 +269,7 @@ for this template
     waiting for device...
     device available
     Get devices for measurement successfully!
-    No: 1   GFLOPS: 3.68/3.68       result: MeasureResult(costs=(0.06287412625000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5222880840301514, timestamp=1673477579.6506963)        [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6853541
-    No: 2   GFLOPS: 101.49/101.49   result: MeasureResult(costs=(0.0022809584999999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.5976881980896, timestamp=1673477580.3919797) [('tile_f', [-1, 8, 2, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9026667
-    No: 3   GFLOPS: 0.00/101.49     result: Traceback (most recent call last):
+    No: 1   GFLOPS: 0.00/0.00       result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -393,8 +391,8 @@ for this template
       File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 32, 4, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2416600
-    No: 4   GFLOPS: 0.00/101.49     result: Traceback (most recent call last):
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 16, 32, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,257224
+    No: 2   GFLOPS: 0.00/0.00       result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -516,626 +514,339 @@ for this template
       File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 2, 4, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,799720
-    No: 5   GFLOPS: 0.00/101.49     result: Traceback (most recent call last):
-      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
-        func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
-      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
-        func = build(s, args, target_host=task.target_host, runtime=runtime)
-      File "/workspace/python/tvm/driver/build_module.py", line 227, in build
-        input_mod = lower(inputs, args, name=name, binds=binds)
-      File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
-        return ffi.lower_schedule(inp, args, name, binds, simple_mode)
-      File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
-      File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
-      File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
-    tvm._ffi.base.TVMError: Traceback (most recent call last):
-      24: TVMFuncCall
-            at ../src/runtime/c_runtime_api.cc:477
-      23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
-            at ../include/tvm/runtime/packed_func.h:1217
-      22: Call
-            at ../include/tvm/runtime/packed_func.h:1213
-      21: operator()
-            at ../include/tvm/runtime/packed_func.h:1730
-      20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
-            at ../include/tvm/runtime/packed_func.h:1670
-      19: run<>
-            at ../include/tvm/runtime/packed_func.h:1630
-      18: run<tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1630
-      17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1630
-      16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1630
-      15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1630
-      14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1645
-      13: operator()
-            at ../src/driver/driver_api.cc:395
-      12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
-            at ../src/driver/driver_api.cc:381
-      11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
-            at ../src/driver/driver_api.cc:276
-      10: tvm::transform::Pass::operator()(tvm::IRModule) const
-            at ../src/ir/transform.cc:258
-      9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
-            at ../src/ir/transform.cc:274
-      8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
-            at ../src/ir/transform.cc:454
-      7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
-            at ../src/ir/transform.cc:274
-      6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
-            at ../src/tir/ir/transform.cc:100
-      5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
-            at ../include/tvm/runtime/packed_func.h:1749
-      4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
-            at ../include/tvm/runtime/packed_func.h:1693
-      3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
-            at ../include/tvm/runtime/packed_func.h:1617
-      2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
-            at ../include/tvm/runtime/packed_func.h:1217
-      1: Call
-            at ../include/tvm/runtime/packed_func.h:1213
-      0: operator()
-            at ../src/runtime/c_runtime_api.cc:534
-      File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
-      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
-        raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
-
-    Traceback (most recent call last):
-      24: TVMFuncCall
-            at ../src/runtime/c_runtime_api.cc:477
-      23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
-            at ../include/tvm/runtime/packed_func.h:1217
-      22: Call
-            at ../include/tvm/runtime/packed_func.h:1213
-      21: operator()
-            at ../include/tvm/runtime/packed_func.h:1730
-      20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
-            at ../include/tvm/runtime/packed_func.h:1670
-      19: run<>
-            at ../include/tvm/runtime/packed_func.h:1630
-      18: run<tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1630
-      17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1630
-      16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1630
-      15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1630
-      14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1645
-      13: operator()
-            at ../src/driver/driver_api.cc:395
-      12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
-            at ../src/driver/driver_api.cc:381
-      11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
-            at ../src/driver/driver_api.cc:276
-      10: tvm::transform::Pass::operator()(tvm::IRModule) const
-            at ../src/ir/transform.cc:258
-      9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
-            at ../src/ir/transform.cc:274
-      8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
-            at ../src/ir/transform.cc:454
-      7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
-            at ../src/ir/transform.cc:274
-      6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
-            at ../src/tir/ir/transform.cc:100
-      5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
-            at ../include/tvm/runtime/packed_func.h:1749
-      4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
-            at ../include/tvm/runtime/packed_func.h:1693
-      3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
-            at ../include/tvm/runtime/packed_func.h:1617
-      2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
-            at ../include/tvm/runtime/packed_func.h:1217
-      1: Call
-            at ../include/tvm/runtime/packed_func.h:1213
-      0: operator()
-            at ../src/runtime/c_runtime_api.cc:534
-      File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
-      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
-        raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 1, 64, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,380914
-    No: 6   GFLOPS: 31.00/101.49    result: MeasureResult(costs=(0.0074668045,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4682140350341797, timestamp=1673477586.0354483)       [('tile_f', [-1, 1, 32, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4936670
-    No: 7   GFLOPS: 0.00/101.49     result: Traceback (most recent call last):
-      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
-        func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
-      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
-        func = build(s, args, target_host=task.target_host, runtime=runtime)
-      File "/workspace/python/tvm/driver/build_module.py", line 227, in build
-        input_mod = lower(inputs, args, name=name, binds=binds)
-      File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
-        return ffi.lower_schedule(inp, args, name, binds, simple_mode)
-      File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
-      File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
-      File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
-    tvm._ffi.base.TVMError: Traceback (most recent call last):
-      24: TVMFuncCall
-            at ../src/runtime/c_runtime_api.cc:477
-      23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
-            at ../include/tvm/runtime/packed_func.h:1217
-      22: Call
-            at ../include/tvm/runtime/packed_func.h:1213
-      21: operator()
-            at ../include/tvm/runtime/packed_func.h:1730
-      20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
-            at ../include/tvm/runtime/packed_func.h:1670
-      19: run<>
-            at ../include/tvm/runtime/packed_func.h:1630
-      18: run<tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1630
-      17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1630
-      16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1630
-      15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1630
-      14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1645
-      13: operator()
-            at ../src/driver/driver_api.cc:395
-      12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
-            at ../src/driver/driver_api.cc:381
-      11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
-            at ../src/driver/driver_api.cc:276
-      10: tvm::transform::Pass::operator()(tvm::IRModule) const
-            at ../src/ir/transform.cc:258
-      9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
-            at ../src/ir/transform.cc:274
-      8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
-            at ../src/ir/transform.cc:454
-      7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
-            at ../src/ir/transform.cc:274
-      6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
-            at ../src/tir/ir/transform.cc:100
-      5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
-            at ../include/tvm/runtime/packed_func.h:1749
-      4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
-            at ../include/tvm/runtime/packed_func.h:1693
-      3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
-            at ../include/tvm/runtime/packed_func.h:1617
-      2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
-            at ../include/tvm/runtime/packed_func.h:1217
-      1: Call
-            at ../include/tvm/runtime/packed_func.h:1213
-      0: operator()
-            at ../src/runtime/c_runtime_api.cc:534
-      File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
-      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
-        raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
-
-    Traceback (most recent call last):
-      24: TVMFuncCall
-            at ../src/runtime/c_runtime_api.cc:477
-      23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
-            at ../include/tvm/runtime/packed_func.h:1217
-      22: Call
-            at ../include/tvm/runtime/packed_func.h:1213
-      21: operator()
-            at ../include/tvm/runtime/packed_func.h:1730
-      20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
-            at ../include/tvm/runtime/packed_func.h:1670
-      19: run<>
-            at ../include/tvm/runtime/packed_func.h:1630
-      18: run<tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1630
-      17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1630
-      16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1630
-      15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1630
-      14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1645
-      13: operator()
-            at ../src/driver/driver_api.cc:395
-      12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
-            at ../src/driver/driver_api.cc:381
-      11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
-            at ../src/driver/driver_api.cc:276
-      10: tvm::transform::Pass::operator()(tvm::IRModule) const
-            at ../src/ir/transform.cc:258
-      9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
-            at ../src/ir/transform.cc:274
-      8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
-            at ../src/ir/transform.cc:454
-      7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
-            at ../src/ir/transform.cc:274
-      6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
-            at ../src/tir/ir/transform.cc:100
-      5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
-            at ../include/tvm/runtime/packed_func.h:1749
-      4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
-            at ../include/tvm/runtime/packed_func.h:1693
-      3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
-            at ../include/tvm/runtime/packed_func.h:1617
-      2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
-            at ../include/tvm/runtime/packed_func.h:1217
-      1: Call
-            at ../include/tvm/runtime/packed_func.h:1213
-      0: operator()
-            at ../src/runtime/c_runtime_api.cc:534
-      File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
-      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
-        raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 1, 16, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6507342
-    No: 8   GFLOPS: 0.00/101.49     result: Traceback (most recent call last):
-      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
-        func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
-      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
-        func = build(s, args, target_host=task.target_host, runtime=runtime)
-      File "/workspace/python/tvm/driver/build_module.py", line 227, in build
-        input_mod = lower(inputs, args, name=name, binds=binds)
-      File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
-        return ffi.lower_schedule(inp, args, name, binds, simple_mode)
-      File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
-      File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
-      File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
-    tvm._ffi.base.TVMError: Traceback (most recent call last):
-      24: TVMFuncCall
-            at ../src/runtime/c_runtime_api.cc:477
-      23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
-            at ../include/tvm/runtime/packed_func.h:1217
-      22: Call
-            at ../include/tvm/runtime/packed_func.h:1213
-      21: operator()
-            at ../include/tvm/runtime/packed_func.h:1730
-      20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
-            at ../include/tvm/runtime/packed_func.h:1670
-      19: run<>
-            at ../include/tvm/runtime/packed_func.h:1630
-      18: run<tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1630
-      17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1630
-      16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1630
-      15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1630
-      14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1645
-      13: operator()
-            at ../src/driver/driver_api.cc:395
-      12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
-            at ../src/driver/driver_api.cc:381
-      11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
-            at ../src/driver/driver_api.cc:276
-      10: tvm::transform::Pass::operator()(tvm::IRModule) const
-            at ../src/ir/transform.cc:258
-      9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
-            at ../src/ir/transform.cc:274
-      8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
-            at ../src/ir/transform.cc:454
-      7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
-            at ../src/ir/transform.cc:274
-      6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
-            at ../src/tir/ir/transform.cc:100
-      5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
-            at ../include/tvm/runtime/packed_func.h:1749
-      4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
-            at ../include/tvm/runtime/packed_func.h:1693
-      3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
-            at ../include/tvm/runtime/packed_func.h:1617
-      2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
-            at ../include/tvm/runtime/packed_func.h:1217
-      1: Call
-            at ../include/tvm/runtime/packed_func.h:1213
-      0: operator()
-            at ../src/runtime/c_runtime_api.cc:534
-      File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
-      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
-        raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
-
-    Traceback (most recent call last):
-      24: TVMFuncCall
-            at ../src/runtime/c_runtime_api.cc:477
-      23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
-            at ../include/tvm/runtime/packed_func.h:1217
-      22: Call
-            at ../include/tvm/runtime/packed_func.h:1213
-      21: operator()
-            at ../include/tvm/runtime/packed_func.h:1730
-      20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
-            at ../include/tvm/runtime/packed_func.h:1670
-      19: run<>
-            at ../include/tvm/runtime/packed_func.h:1630
-      18: run<tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1630
-      17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1630
-      16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1630
-      15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1630
-      14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1645
-      13: operator()
-            at ../src/driver/driver_api.cc:395
-      12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
-            at ../src/driver/driver_api.cc:381
-      11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
-            at ../src/driver/driver_api.cc:276
-      10: tvm::transform::Pass::operator()(tvm::IRModule) const
-            at ../src/ir/transform.cc:258
-      9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
-            at ../src/ir/transform.cc:274
-      8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
-            at ../src/ir/transform.cc:454
-      7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
-            at ../src/ir/transform.cc:274
-      6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
-            at ../src/tir/ir/transform.cc:100
-      5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
-            at ../include/tvm/runtime/packed_func.h:1749
-      4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
-            at ../include/tvm/runtime/packed_func.h:1693
-      3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
-            at ../include/tvm/runtime/packed_func.h:1617
-      2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
-            at ../include/tvm/runtime/packed_func.h:1217
-      1: Call
-            at ../include/tvm/runtime/packed_func.h:1213
-      0: operator()
-            at ../src/runtime/c_runtime_api.cc:534
-      File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
-      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
-        raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 64, 8, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9308453
-    No: 9   GFLOPS: 0.00/101.49     result: Traceback (most recent call last):
-      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
-        func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
-      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
-        func = build(s, args, target_host=task.target_host, runtime=runtime)
-      File "/workspace/python/tvm/driver/build_module.py", line 227, in build
-        input_mod = lower(inputs, args, name=name, binds=binds)
-      File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
-        return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 16, 2, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7273312
+    No: 3   GFLOPS: 1.33/1.33       result: MeasureResult(costs=(0.17353095999999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.83182430267334, timestamp=1673502132.7050912)  [('tile_f', [-1, 8, 2, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5682931
+    No: 4   GFLOPS: 0.00/1.33       result: Traceback (most recent call last):
+      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
+        res = future.result()
+      File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
+        return self.__get_result()
+      File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
+        raise self._exception
+      File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
+        result = self.fn(*self.args, **self.kwargs)
+      File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
+        worker = lambda *args: self._worker_run(*args)
+      File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
+        return proc.recv()
+      File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
+        raise TimeoutError()
+    TimeoutError
+
+            [('tile_f', [-1, 16, 1, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10166919
+    No: 5   GFLOPS: 1.48/1.48       result: MeasureResult(costs=(0.15661549375,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.321930408477783, timestamp=1673502137.493335)        [('tile_f', [-1, 2, 1, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5982021
+    No: 6   GFLOPS: 45.73/45.73     result: MeasureResult(costs=(0.0050626560000000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7475886344909668, timestamp=1673502138.2436917)      [('tile_f', [-1, 1, 16, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4687519
+    No: 7   GFLOPS: 0.00/45.73      result: Traceback (most recent call last):
+      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 742, in __call__
+        yield remote, remote.load_module(os.path.split(build_result.filename)[1])
+      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
+        costs = time_f(*args).results
+      File "/workspace/python/tvm/runtime/module.py", line 357, in evaluator
+        blob = feval(*args)
       File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
-      File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+      File "tvm/_ffi/_cython/./packed_func.pxi", line 262, in tvm._ffi._cy3.core.FuncCall
+      File "tvm/_ffi/_cython/./packed_func.pxi", line 251, in tvm._ffi._cy3.core.FuncCall3
       File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
     tvm._ffi.base.TVMError: Traceback (most recent call last):
-      24: TVMFuncCall
+      4: TVMFuncCall
             at ../src/runtime/c_runtime_api.cc:477
-      23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
-            at ../include/tvm/runtime/packed_func.h:1217
-      22: Call
-            at ../include/tvm/runtime/packed_func.h:1213
-      21: operator()
-            at ../include/tvm/runtime/packed_func.h:1730
-      20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
-            at ../include/tvm/runtime/packed_func.h:1670
-      19: run<>
-            at ../include/tvm/runtime/packed_func.h:1630
-      18: run<tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1630
-      17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1630
-      16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1630
-      15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1630
-      14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1645
-      13: operator()
-            at ../src/driver/driver_api.cc:395
-      12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
-            at ../src/driver/driver_api.cc:381
-      11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
-            at ../src/driver/driver_api.cc:276
-      10: tvm::transform::Pass::operator()(tvm::IRModule) const
-            at ../src/ir/transform.cc:258
-      9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
-            at ../src/ir/transform.cc:274
-      8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
-            at ../src/ir/transform.cc:454
-      7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
-            at ../src/ir/transform.cc:274
-      6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
-            at ../src/tir/ir/transform.cc:100
-      5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
-            at ../include/tvm/runtime/packed_func.h:1749
-      4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
-            at ../include/tvm/runtime/packed_func.h:1693
-      3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
-            at ../include/tvm/runtime/packed_func.h:1617
-      2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+      3: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
             at ../include/tvm/runtime/packed_func.h:1217
-      1: Call
-            at ../include/tvm/runtime/packed_func.h:1213
-      0: operator()
-            at ../src/runtime/c_runtime_api.cc:534
-      File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
-      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
-        raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
+      2: tvm::runtime::RPCWrappedFunc::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+            at ../src/runtime/rpc/rpc_module.cc:129
+      1: tvm::runtime::RPCClientSession::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)> const&)
+            at ../src/runtime/rpc/rpc_endpoint.cc:1012
+      0: tvm::runtime::RPCEndpoint::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)>)
+            at ../src/runtime/rpc/rpc_endpoint.cc:804
+      File "../src/runtime/rpc/rpc_endpoint.cc", line 804
+    TVMError: 
+    ---------------------------------------------------------------
+    An error occurred during the execution of TVM.
+    For more information, please see: https://tvm.apache.org/docs/errors.html
+    ---------------------------------------------------------------
+      Check failed: (code == RPCCode::kReturn) is false: code=kShutdown
+
+    During handling of the above exception, another exception occurred:
 
     Traceback (most recent call last):
-      24: TVMFuncCall
-            at ../src/runtime/c_runtime_api.cc:477
-      23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
-            at ../include/tvm/runtime/packed_func.h:1217
-      22: Call
-            at ../include/tvm/runtime/packed_func.h:1213
-      21: operator()
-            at ../include/tvm/runtime/packed_func.h:1730
-      20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
-            at ../include/tvm/runtime/packed_func.h:1670
-      19: run<>
-            at ../include/tvm/runtime/packed_func.h:1630
-      18: run<tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1630
-      17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1630
-      16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1630
-      15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1630
-      14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1645
-      13: operator()
-            at ../src/driver/driver_api.cc:395
-      12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
-            at ../src/driver/driver_api.cc:381
-      11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
-            at ../src/driver/driver_api.cc:276
-      10: tvm::transform::Pass::operator()(tvm::IRModule) const
-            at ../src/ir/transform.cc:258
-      9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
-            at ../src/ir/transform.cc:274
-      8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
-            at ../src/ir/transform.cc:454
-      7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
-            at ../src/ir/transform.cc:274
-      6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
-            at ../src/tir/ir/transform.cc:100
-      5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
-            at ../include/tvm/runtime/packed_func.h:1749
-      4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
-            at ../include/tvm/runtime/packed_func.h:1693
-      3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
+        costs = time_f(*args).results
+      File "/usr/lib/python3.7/contextlib.py", line 130, in __exit__
+        self.gen.throw(type, value, traceback)
+      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 746, in __call__
+        remote.remove(build_result.filename)
+      File "/workspace/python/tvm/rpc/client.py", line 144, in remove
+        self._remote_funcs["remove"] = self.get_function("tvm.rpc.server.remove")
+      File "/workspace/python/tvm/rpc/client.py", line 72, in get_function
+        return self._sess.get_function(name)
+      File "/workspace/python/tvm/runtime/module.py", line 171, in get_function
+        self.handle, c_str(name), ctypes.c_int(query_imports), ctypes.byref(ret_handle)
+      File "/workspace/python/tvm/_ffi/base.py", line 348, in check_call
+        raise get_last_ffi_error()
+    tvm._ffi.base.TVMError: Traceback (most recent call last):
+      52: 0xffffffffffffffff
+      51: _start
+      50: __libc_start_main
+      49: _Py_UnixMain
+      48: 0x0000000000650da0
+      47: 0x0000000000650afa
+      46: _PyFunction_FastCallDict
+      45: _PyEval_EvalCodeWithName
+      44: _PyEval_EvalFrameDefault
+      43: _PyFunction_FastCallKeywords
+      42: _PyEval_EvalCodeWithName
+      41: _PyEval_EvalFrameDefault
+      40: _PyMethodDef_RawFastCallKeywords
+      39: 0x0000000000546369
+      38: _PyEval_EvalCodeWithName
+      37: _PyEval_EvalFrameDefault
+      36: _PyFunction_FastCallKeywords
+      35: _PyEval_EvalCodeWithName
+      34: _PyEval_EvalFrameDefault
+      33: _PyFunction_FastCallDict
+      32: _PyEval_EvalCodeWithName
+      31: _PyEval_EvalFrameDefault
+      30: _PyObject_FastCallDict
+      29: 0x00000000004c06e1
+      28: _PyFunction_FastCallDict
+      27: _PyEval_EvalFrameDefault
+      26: _PyMethodDescr_FastCallKeywords
+      25: 0x00000000005dcb58
+      24: 0x00000000005dc83f
+      23: 0x00000000004ba127
+      22: _PyEval_EvalFrameDefault
+      21: _PyFunction_FastCallKeywords
+      20: _PyEval_EvalFrameDefault
+      19: _PyFunction_FastCallKeywords
+      18: _PyEval_EvalFrameDefault
+      17: _PyFunction_FastCallKeywords
+      16: _PyEval_EvalCodeWithName
+      15: _PyEval_EvalFrameDefault
+      14: 0x0000000000537c30
+      13: _PyObject_FastCallKeywords
+      12: 0x00007f948c9d9fa2
+      11: _ctypes_callproc
+      10: ffi_call
+      9: ffi_call_unix64
+      8: TVMModGetFunction
+            at ../src/runtime/c_runtime_api.cc:408
+      7: tvm::runtime::ModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, bool)
+            at ../src/runtime/module.cc:66
+      6: tvm::runtime::RPCModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)
+            at ../src/runtime/rpc/rpc_module.cc:185
+      5: tvm::runtime::RPCClientSession::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
+            at ../src/runtime/rpc/rpc_endpoint.cc:1007
+      4: tvm::runtime::TVMRetValue tvm::runtime::RPCEndpoint::SysCallRemote<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(tvm::runtime::RPCCode, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
+            at ../src/runtime/rpc/rpc_endpoint.h:223
+      3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(int&&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) const
             at ../include/tvm/runtime/packed_func.h:1617
       2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
             at ../include/tvm/runtime/packed_func.h:1217
       1: Call
             at ../include/tvm/runtime/packed_func.h:1213
       0: operator()
-            at ../src/runtime/c_runtime_api.cc:534
-      File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
-      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
-        raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 8, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,490242
-    No: 10  GFLOPS: 32.78/101.49    result: MeasureResult(costs=(0.0070626068,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6557199954986572, timestamp=1673477588.086393)        [('tile_f', [-1, 1, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5360684
-    No: 11  GFLOPS: 0.00/101.49     result: Traceback (most recent call last):
-      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
-        func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
-      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
-        func = build(s, args, target_host=task.target_host, runtime=runtime)
-      File "/workspace/python/tvm/driver/build_module.py", line 227, in build
-        input_mod = lower(inputs, args, name=name, binds=binds)
-      File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
-        return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+            at ../src/runtime/rpc/rpc_endpoint.cc:684
+      File "../src/runtime/rpc/rpc_endpoint.cc", line 684
+    TVMError: 
+    ---------------------------------------------------------------
+    An error occurred during the execution of TVM.
+    For more information, please see: https://tvm.apache.org/docs/errors.html
+    ---------------------------------------------------------------
+      Check failed: (code == RPCCode::kReturn) is false: code=1
+
+    Traceback (most recent call last):
+      52: 0xffffffffffffffff
+      51: _start
+      50: __libc_start_main
+      49: _Py_UnixMain
+      48: 0x0000000000650da0
+      47: 0x0000000000650afa
+      46: _PyFunction_FastCallDict
+      45: _PyEval_EvalCodeWithName
+      44: _PyEval_EvalFrameDefault
+      43: _PyFunction_FastCallKeywords
+      42: _PyEval_EvalCodeWithName
+      41: _PyEval_EvalFrameDefault
+      40: _PyMethodDef_RawFastCallKeywords
+      39: 0x0000000000546369
+      38: _PyEval_EvalCodeWithName
+      37: _PyEval_EvalFrameDefault
+      36: _PyFunction_FastCallKeywords
+      35: _PyEval_EvalCodeWithName
+      34: _PyEval_EvalFrameDefault
+      33: _PyFunction_FastCallDict
+      32: _PyEval_EvalCodeWithName
+      31: _PyEval_EvalFrameDefault
+      30: _PyObject_FastCallDict
+      29: 0x00000000004c06e1
+      28: _PyFunction_FastCallDict
+      27: _PyEval_EvalFrameDefault
+      26: _PyMethodDescr_FastCallKeywords
+      25: 0x00000000005dcb58
+      24: 0x00000000005dc83f
+      23: 0x00000000004ba127
+      22: _PyEval_EvalFrameDefault
+      21: _PyFunction_FastCallKeywords
+      20: _PyEval_EvalFrameDefault
+      19: _PyFunction_FastCall      [('tile_f', [-1, 2, 1, 64]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,128021
+    No: 8   GFLOPS: 51.91/51.91     result: MeasureResult(costs=(0.004459976173913044,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.441880702972412, timestamp=1673502144.4836936)        [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1012880
+    No: 9   GFLOPS: 89.08/89.08     result: MeasureResult(costs=(0.002598741311111111,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.791047811508179, timestamp=1673502150.4239016)        [('tile_f', [-1, 1, 2, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8797063
+    No: 10  GFLOPS: 0.00/89.08      result: Traceback (most recent call last):
+      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 742, in __call__
+        yield remote, remote.load_module(os.path.split(build_result.filename)[1])
+      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
+        costs = time_f(*args).results
+      File "/workspace/python/tvm/runtime/module.py", line 357, in evaluator
+        blob = feval(*args)
       File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
-      File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+      File "tvm/_ffi/_cython/./packed_func.pxi", line 262, in tvm._ffi._cy3.core.FuncCall
+      File "tvm/_ffi/_cython/./packed_func.pxi", line 251, in tvm._ffi._cy3.core.FuncCall3
       File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
     tvm._ffi.base.TVMError: Traceback (most recent call last):
-      24: TVMFuncCall
+      4: TVMFuncCall
             at ../src/runtime/c_runtime_api.cc:477
-      23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
-            at ../include/tvm/runtime/packed_func.h:1217
-      22: Call
-            at ../include/tvm/runtime/packed_func.h:1213
-      21: operator()
-            at ../include/tvm/runtime/packed_func.h:1730
-      20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
-            at ../include/tvm/runtime/packed_func.h:1670
-      19: run<>
-            at ../include/tvm/runtime/packed_func.h:1630
-      18: run<tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1630
-      17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1630
-      16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1630
-      15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1630
-      14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1645
-      13: operator()
-            at ../src/driver/driver_api.cc:395
-      12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
-            at ../src/driver/driver_api.cc:381
-      11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
-            at ../src/driver/driver_api.cc:276
-      10: tvm::transform::Pass::operator()(tvm::IRModule) const
-            at ../src/ir/transform.cc:258
-      9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
-            at ../src/ir/transform.cc:274
-      8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
-            at ../src/ir/transform.cc:454
-      7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
-            at ../src/ir/transform.cc:274
-      6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
-            at ../src/tir/ir/transform.cc:100
-      5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
-            at ../include/tvm/runtime/packed_func.h:1749
-      4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
-            at ../include/tvm/runtime/packed_func.h:1693
-      3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
-            at ../include/tvm/runtime/packed_func.h:1617
-      2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+      3: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
             at ../include/tvm/runtime/packed_func.h:1217
-      1: Call
-            at ../include/tvm/runtime/packed_func.h:1213
-      0: operator()
-            at ../src/runtime/c_runtime_api.cc:534
-      File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
-      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
-        raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
+      2: tvm::runtime::RPCWrappedFunc::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+            at ../src/runtime/rpc/rpc_module.cc:129
+      1: tvm::runtime::RPCClientSession::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)> const&)
+            at ../src/runtime/rpc/rpc_endpoint.cc:1012
+      0: tvm::runtime::RPCEndpoint::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)>)
+            at ../src/runtime/rpc/rpc_endpoint.cc:804
+      File "../src/runtime/rpc/rpc_endpoint.cc", line 804
+    TVMError: 
+    ---------------------------------------------------------------
+    An error occurred during the execution of TVM.
+    For more information, please see: https://tvm.apache.org/docs/errors.html
+    ---------------------------------------------------------------
+      Check failed: (code == RPCCode::kReturn) is false: code=kShutdown
+
+    During handling of the above exception, another exception occurred:
 
     Traceback (most recent call last):
-      24: TVMFuncCall
-            at ../src/runtime/c_runtime_api.cc:477
-      23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
-            at ../include/tvm/runtime/packed_func.h:1217
-      22: Call
-            at ../include/tvm/runtime/packed_func.h:1213
-      21: operator()
-            at ../include/tvm/runtime/packed_func.h:1730
-      20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
-            at ../include/tvm/runtime/packed_func.h:1670
-      19: run<>
-            at ../include/tvm/runtime/packed_func.h:1630
-      18: run<tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1630
-      17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1630
-      16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1630
-      15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1630
-      14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
-            at ../include/tvm/runtime/packed_func.h:1645
-      13: operator()
-            at ../src/driver/driver_api.cc:395
-      12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
-            at ../src/driver/driver_api.cc:381
-      11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
-            at ../src/driver/driver_api.cc:276
-      10: tvm::transform::Pass::operator()(tvm::IRModule) const
-            at ../src/ir/transform.cc:258
-      9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
-            at ../src/ir/transform.cc:274
-      8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
-            at ../src/ir/transform.cc:454
-      7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
-            at ../src/ir/transform.cc:274
-      6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
-            at ../src/tir/ir/transform.cc:100
-      5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
-            at ../include/tvm/runtime/packed_func.h:1749
-      4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
-            at ../include/tvm/runtime/packed_func.h:1693
-      3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
+        costs = time_f(*args).results
+      File "/usr/lib/python3.7/contextlib.py", line 130, in __exit__
+        self.gen.throw(type, value, traceback)
+      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 746, in __call__
+        remote.remove(build_result.filename)
+      File "/workspace/python/tvm/rpc/client.py", line 144, in remove
+        self._remote_funcs["remove"] = self.get_function("tvm.rpc.server.remove")
+      File "/workspace/python/tvm/rpc/client.py", line 72, in get_function
+        return self._sess.get_function(name)
+      File "/workspace/python/tvm/runtime/module.py", line 171, in get_function
+        self.handle, c_str(name), ctypes.c_int(query_imports), ctypes.byref(ret_handle)
+      File "/workspace/python/tvm/_ffi/base.py", line 348, in check_call
+        raise get_last_ffi_error()
+    tvm._ffi.base.TVMError: Traceback (most recent call last):
+      52: 0xffffffffffffffff
+      51: _start
+      50: __libc_start_main
+      49: _Py_UnixMain
+      48: 0x0000000000650da0
+      47: 0x0000000000650afa
+      46: _PyFunction_FastCallDict
+      45: _PyEval_EvalCodeWithName
+      44: _PyEval_EvalFrameDefault
+      43: _PyFunction_FastCallKeywords
+      42: _PyEval_EvalCodeWithName
+      41: _PyEval_EvalFrameDefault
+      40: _PyMethodDef_RawFastCallKeywords
+      39: 0x0000000000546369
+      38: _PyEval_EvalCodeWithName
+      37: _PyEval_EvalFrameDefault
+      36: _PyFunction_FastCallKeywords
+      35: _PyEval_EvalCodeWithName
+      34: _PyEval_EvalFrameDefault
+      33: _PyFunction_FastCallDict
+      32: _PyEval_EvalCodeWithName
+      31: _PyEval_EvalFrameDefault
+      30: _PyObject_FastCallDict
+      29: 0x00000000004c06e1
+      28: _PyFunction_FastCallDict
+      27: _PyEval_EvalFrameDefault
+      26: _PyMethodDescr_FastCallKeywords
+      25: 0x00000000005dcb58
+      24: 0x00000000005dc83f
+      23: 0x00000000004ba127
+      22: _PyEval_EvalFrameDefault
+      21: _PyFunction_FastCallKeywords
+      20: _PyEval_EvalFrameDefault
+      19: _PyFunction_FastCallKeywords
+      18: _PyEval_EvalFrameDefault
+      17: _PyFunction_FastCallKeywords
+      16: _PyEval_EvalCodeWithName
+      15: _PyEval_EvalFrameDefault
+      14: 0x0000000000537c30
+      13: _PyObject_FastCallKeywords
+      12: 0x00007fe0c1fd7fa2
+      11: _ctypes_callproc
+      10: ffi_call
+      9: ffi_call_unix64
+      8: TVMModGetFunction
+            at ../src/runtime/c_runtime_api.cc:408
+      7: tvm::runtime::ModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, bool)
+            at ../src/runtime/module.cc:66
+      6: tvm::runtime::RPCModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)
+            at ../src/runtime/rpc/rpc_module.cc:185
+      5: tvm::runtime::RPCClientSession::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
+            at ../src/runtime/rpc/rpc_endpoint.cc:1007
+      4: tvm::runtime::TVMRetValue tvm::runtime::RPCEndpoint::SysCallRemote<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(tvm::runtime::RPCCode, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
+            at ../src/runtime/rpc/rpc_endpoint.h:223
+      3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(int&&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) const
             at ../include/tvm/runtime/packed_func.h:1617
       2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
             at ../include/tvm/runtime/packed_func.h:1217
       1: Call
             at ../include/tvm/runtime/packed_func.h:1213
       0: operator()
-            at ../src/runtime/c_runtime_api.cc:534
-      File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
-      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
-        raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 256, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3058898
-    No: 12  GFLOPS: 174.82/174.82   result: MeasureResult(costs=(0.001324242594936709,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7749338150024414, timestamp=1673477588.8270257)       [('tile_f', [-1, 4, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2181532
-    No: 13  GFLOPS: 0.00/174.82     result: Traceback (most recent call last):
+            at ../src/runtime/rpc/rpc_endpoint.cc:684
+      File "../src/runtime/rpc/rpc_endpoint.cc", line 684
+    TVMError: 
+    ---------------------------------------------------------------
+    An error occurred during the execution of TVM.
+    For more information, please see: https://tvm.apache.org/docs/errors.html
+    ---------------------------------------------------------------
+      Check failed: (code == RPCCode::kReturn) is false: code=1
+
+    Traceback (most recent call last):
+      52: 0xffffffffffffffff
+      51: _start
+      50: __libc_start_main
+      49: _Py_UnixMain
+      48: 0x0000000000650da0
+      47: 0x0000000000650afa
+      46: _PyFunction_FastCallDict
+      45: _PyEval_EvalCodeWithName
+      44: _PyEval_EvalFrameDefault
+      43: _PyFunction_FastCallKeywords
+      42: _PyEval_EvalCodeWithName
+      41: _PyEval_EvalFrameDefault
+      40: _PyMethodDef_RawFastCallKeywords
+      39: 0x0000000000546369
+      38: _PyEval_EvalCodeWithName
+      37: _PyEval_EvalFrameDefault
+      36: _PyFunction_FastCallKeywords
+      35: _PyEval_EvalCodeWithName
+      34: _PyEval_EvalFrameDefault
+      33: _PyFunction_FastCallDict
+      32: _PyEval_EvalCodeWithName
+      31: _PyEval_EvalFrameDefault
+      30: _PyObject_FastCallDict
+      29: 0x00000000004c06e1
+      28: _PyFunction_FastCallDict
+      27: _PyEval_EvalFrameDefault
+      26: _PyMethodDescr_FastCallKeywords
+      25: 0x00000000005dcb58
+      24: 0x00000000005dc83f
+      23: 0x00000000004ba127
+      22: _PyEval_EvalFrameDefault
+      21: _PyFunction_FastCallKeywords
+      20: _PyEval_EvalFrameDefault
+      19: _PyFunction_FastCall      [('tile_f', [-1, 16, 1, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4295228
+    No: 11  GFLOPS: 99.63/99.63     result: MeasureResult(costs=(0.002323559956521739,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.8995442390441895, timestamp=1673502155.9981914)       [('tile_f', [-1, 16, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9304244
+    No: 12  GFLOPS: 312.41/312.41   result: MeasureResult(costs=(0.0007410120073529412,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.656644582748413, timestamp=1673502156.7293446)       [('tile_f', [-1, 4, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6707821
+    No: 13  GFLOPS: 0.00/312.41     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1257,8 +968,8 @@ for this template
       File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 1, 128, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,582609
-    No: 14  GFLOPS: 0.00/174.82     result: Traceback (most recent call last):
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 2, 128, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3748190
+    No: 14  GFLOPS: 0.00/312.41     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1380,8 +1091,8 @@ for this template
       File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 8, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10348924
-    No: 15  GFLOPS: 0.00/174.82     result: Traceback (most recent call last):
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 1, 256, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2600059
+    No: 15  GFLOPS: 0.00/312.41     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1503,8 +1214,8 @@ for this template
       File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 16, 1, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3024529
-    No: 16  GFLOPS: 0.00/174.82     result: Traceback (most recent call last):
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 16, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2880124
+    No: 16  GFLOPS: 0.00/312.41     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1626,8 +1337,8 @@ for this template
       File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 128, 4, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10368406
-    No: 17  GFLOPS: 0.00/174.82     result: Traceback (most recent call last):
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 1, 1, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3373225
+    No: 17  GFLOPS: 0.00/312.41     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1749,8 +1460,8 @@ for this template
       File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7124053
-    No: 18  GFLOPS: 0.00/174.82     result: Traceback (most recent call last):
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 1, 2, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6504663
+    No: 18  GFLOPS: 0.00/312.41     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1872,9 +1583,9 @@ for this template
       File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 16, 4, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8372176
-    No: 19  GFLOPS: 359.92/359.92   result: MeasureResult(costs=(0.0006432020443037976,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.531822919845581, timestamp=1673477590.7701168)       [('tile_f', [-1, 4, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9942321
-    No: 20  GFLOPS: 0.00/359.92     result: Traceback (most recent call last):
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 2, 2, 64]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7605385
+    No: 19  GFLOPS: 326.86/326.86   result: MeasureResult(costs=(0.000708254314159292,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3503572940826416, timestamp=1673502158.5269222)       [('tile_f', [-1, 2, 16, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6399006
+    No: 20  GFLOPS: 0.00/326.86     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1996,7 +1707,7 @@ for this template
       File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 8, 32, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3659793
+    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, 7]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2259164
 
 
 
@@ -2051,9 +1762,9 @@ and measure running time.
     Finish loading 20 records
 
     Best config:
-    [('tile_f', [-1, 4, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9942321
+    [('tile_f', [-1, 2, 16, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6399006
     Finish loading 20 records
-    Time cost of this operator: 0.001173
+    Time cost of this operator: 0.001048
 
 
 
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 1be8c1e90e..619057401a 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
@@ -368,10 +368,10 @@ Timing the untuned program
     ########## Build without Autotuning ##########
     Node Name                                     Ops                                           Time(us)  Time(%)  Shape              Inputs  Outputs  Measurements(us)  
     ---------                                     ---                                           --------  -------  -----              ------  -------  ----------------  
-    tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  312.2     98.73    (1, 2, 10, 10, 3)  2       1        [312.2]           
-    tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       3.039     0.961    (1, 6, 10, 10)     1       1        [3.039]           
-    tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.978     0.309    (1, 1, 10, 10, 3)  1       1        [0.978]           
-    Total_time                                    -                                             316.216   -        -                  -       -        -                 
+    tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  311.6     98.734   (1, 2, 10, 10, 3)  2       1        [311.6]           
+    tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       3.021     0.957    (1, 6, 10, 10)     1       1        [3.021]           
+    tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.975     0.309    (1, 1, 10, 10, 3)  1       1        [0.975]           
+    Total_time                                    -                                             315.596   -        -                  -       -        -                 
 
 
 
@@ -436,10 +436,10 @@ Timing the tuned program
     ########## Build with Autotuning ##########
     Node Name                                     Ops                                           Time(us)  Time(%)  Shape              Inputs  Outputs  Measurements(us)  
     ---------                                     ---                                           --------  -------  -----              ------  -------  ----------------  
-    tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  100.4     97.221   (1, 6, 10, 10, 1)  2       1        [100.4]           
-    tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       1.768     1.712    (1, 6, 10, 10)     1       1        [1.768]           
-    tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         1.102     1.067    (1, 1, 10, 10, 3)  1       1        [1.102]           
-    Total_time                                    -                                             103.27    -        -                  -       -        -                 
+    tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  115.4     97.708   (1, 6, 10, 10, 1)  2       1        [115.4]           
+    tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       1.753     1.484    (1, 6, 10, 10)     1       1        [1.753]           
+    tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.954     0.808    (1, 1, 10, 10, 3)  1       1        [0.954]           
+    Total_time                                    -                                             118.107   -        -                  -       -        -                 
 
 
 
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
index 9b86ef4abc..0dc7f62cae 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
@@ -117,7 +117,7 @@ download a cat image and preprocess it to use as the model input.
     /venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/ao/quantization/utils.py:281: UserWarning: must run observer before calling calculate_qparams. Returning default values.
       "must run observer before calling calculate_qparams. " +
     Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
-
      0%|          | 0.00/3.42M [00:00<?, ?B/s]
     61%|######    | 2.09M/3.42M [00:00<00:00, 19.4MB/s]
    100%|##########| 3.42M/3.42M [00:00<00:00, 30.3MB/s]
+
      0%|          | 0.00/3.42M [00:00<?, ?B/s]
    100%|##########| 3.42M/3.42M [00:00<00:00, 47.8MB/s]
     /workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
       return LooseVersion(torch_ver) > ver
     /venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -322,7 +322,7 @@ Look up prediction top 1 index in 1000 class synset.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  5.483 seconds)
+   **Total running time of the script:** ( 1 minutes  2.950 seconds)
 
 
 .. _sphx_glr_download_how_to_work_with_microtvm_micro_pytorch.py:
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
index f2bb2cc4a8..741a7c0947 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
@@ -218,7 +218,7 @@ take about **2 minutes** to download the Stanford Cars, while COCO 2017 validati
  .. code-block:: none
 
 
-    '/tmp/tmpokx4fnxp/images/random'
+    '/tmp/tmp_em5wk7k/images/random'
 
 
 
@@ -318,8 +318,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
 
  .. code-block:: none
 
-    /tmp/tmpokx4fnxp/images/target contains 8144 images
-    /tmp/tmpokx4fnxp/images/random contains 5000 images
+    /tmp/tmp_em5wk7k/images/target contains 8144 images
+    /tmp/tmp_em5wk7k/images/random contains 5000 images
 
 
 
@@ -494,13 +494,13 @@ the time on our validation set).
  .. code-block:: none
 
     Epoch 1/3
-    328/328 - 48s - loss: 0.2235 - accuracy: 0.9233 - val_loss: 0.1560 - val_accuracy: 0.9528 - 48s/epoch - 146ms/step
+    328/328 - 47s - loss: 0.2261 - accuracy: 0.9262 - val_loss: 0.1502 - val_accuracy: 0.9494 - 47s/epoch - 143ms/step
     Epoch 2/3
-    328/328 - 44s - loss: 0.0895 - accuracy: 0.9674 - val_loss: 0.1484 - val_accuracy: 0.9558 - 44s/epoch - 134ms/step
+    328/328 - 44s - loss: 0.0904 - accuracy: 0.9666 - val_loss: 0.1393 - val_accuracy: 0.9547 - 44s/epoch - 133ms/step
     Epoch 3/3
-    328/328 - 44s - loss: 0.0645 - accuracy: 0.9749 - val_loss: 0.1437 - val_accuracy: 0.9528 - 44s/epoch - 133ms/step
+    328/328 - 43s - loss: 0.0647 - accuracy: 0.9761 - val_loss: 0.1286 - val_accuracy: 0.9619 - 43s/epoch - 132ms/step
 
-    <keras.callbacks.History object at 0x7f2ac64e0210>
+    <keras.callbacks.History object at 0x7f30f5124cd0>
 
 
 
@@ -857,7 +857,7 @@ Arduino tutorial for how to do that `on GitHub <https://github.com/guberti/tvm-a
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 4 minutes  39.342 seconds)
+   **Total running time of the script:** ( 4 minutes  20.440 seconds)
 
 
 .. _sphx_glr_download_how_to_work_with_microtvm_micro_train.py:
diff --git a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
index 243d0d9053..70f1f92dc1 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
 
 Computation times
 =================
-**06:49.993** total execution time for **how_to_work_with_microtvm** files:
+**06:26.619** total execution time for **how_to_work_with_microtvm** files:
 
 +---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``)               | 04:39.342 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``)               | 04:20.440 | 0.0 MB |
 +---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``)           | 01:05.483 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``)           | 01:02.950 | 0.0 MB |
 +---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)         | 00:53.206 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)         | 00:51.524 | 0.0 MB |
 +---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``)                   | 00:08.030 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``)                   | 00:07.887 | 0.0 MB |
 +---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)             | 00:03.930 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)             | 00:03.815 | 0.0 MB |
 +---------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.py``) | 00:00.001 | 0.0 MB |
 +---------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index 03dd454071..e3e3a0b5a6 100644
--- a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
 
 Computation times
 =================
-**00:45.487** total execution time for **how_to_work_with_relay** files:
+**00:44.322** total execution time for **how_to_work_with_relay** files:
 
 +----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:33.491 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:32.262 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)           | 00:10.269 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)           | 00:10.366 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)                             | 00:01.720 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)                             | 00:01.687 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``)                 | 00:00.007 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``)                 | 00:00.008 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
index fcfbef5d7f..63465bc7c4 100644
--- a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
@@ -265,7 +265,7 @@ The following example customizes CUDA lowering rule for :code:`exp`.
  .. code-block:: none
 
 
-    <function my_cuda_math_rule at 0x7f2a5a819830>
+    <function my_cuda_math_rule at 0x7f316f7730e0>
 
 
 
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 b536dd54a3..85501cff62 100644
--- a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
@@ -5,22 +5,22 @@
 
 Computation times
 =================
-**00:07.153** total execution time for **how_to_work_with_schedules** files:
+**00:07.198** total execution time for **how_to_work_with_schedules** files:
 
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)                 | 00:04.624 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)                 | 00:04.713 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)                     | 00:01.132 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)                     | 00:01.134 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)                     | 00:00.599 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)                     | 00:00.576 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)                               | 00:00.574 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)                               | 00:00.559 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)                     | 00:00.118 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)                     | 00:00.114 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.052 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.049 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)                               | 00:00.029 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``)               | 00:00.024 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``)               | 00:00.025 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
index b2aa5bc836..84dead301b 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -347,7 +347,7 @@ The importing needs to happen before the tensorized GEMV being executed.
                  B: Buffer(B_2: Pointer(float32), float32, [512, 64], []),
                  C: Buffer(C_2: Pointer(float32), float32, [1024, 512], [])}
       buffer_map = {A_1: A, B_1: B, C_1: C} {
-      attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpx6r84cg2/input0.cc'\nsource_filename = \"/tmp/tmpx6r84cg2/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/tmp_3qzciin/input0.cc'\nsource_filename = \"/tmp/tmp_3qzciin/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 d0cb88dfba..e08064c427 100644
--- a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
 
 Computation times
 =================
-**00:27.015** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:26.016** total execution time for **topic_vta_tutorials_autotvm** files:
 
 +---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:27.008 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:26.010 | 0.0 MB |
 +---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``)     | 00:00.007 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``)     | 00:00.006 | 0.0 MB |
 +---------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
index 90f2c23592..f66c02c8a3 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -293,7 +293,7 @@ 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 30.08s!
+    resnet18_v1 inference graph built in 28.71s!
 
 
 
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 37468e27db..0c91198940 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -337,7 +337,7 @@ The compilation steps are:
 
     /workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
       DeprecationWarning,
-    yolov3-tiny inference graph built in 20.24s!
+    yolov3-tiny inference graph built in 19.57s!
 
 
 
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 d0f4579981..ee3ce8d503 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
 
 Computation times
 =================
-**01:34.126** total execution time for **topic_vta_tutorials_frontend** files:
+**01:31.992** total execution time for **topic_vta_tutorials_frontend** files:
 
 +------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)           | 00:47.132 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)           | 00:46.388 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:46.994 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:45.604 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
index ef180b8b5a..f4cf721079 100644
--- a/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
 
 Computation times
 =================
-**00:03.195** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.158** total execution time for **topic_vta_tutorials_optimize** files:
 
 +--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)         | 00:02.714 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)         | 00:02.702 | 0.0 MB |
 +--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.481 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.455 | 0.0 MB |
 +--------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
index 7e9de6d42f..2780bee0fd 100644
--- a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
 
 Computation times
 =================
-**00:00.837** total execution time for **topic_vta_tutorials** files:
+**00:00.807** total execution time for **topic_vta_tutorials** files:
 
 +---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.444 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.423 | 0.0 MB |
 +---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.394 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.384 | 0.0 MB |
 +---------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
index bea463f0b3..238c15b533 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -207,6 +207,13 @@ trials, we can load the best schedule from the log file and apply it.
 
 
 
+.. rst-class:: sphx-glr-script-out
+
+ .. code-block:: none
+
+    *E
+
+
 
 
 
@@ -329,7 +336,7 @@ We build the binary and check its correctness and performance.
 
  .. code-block:: none
 
-    Execution time of this operator: 96.003 ms
+    Execution time of this operator: 95.922 ms
 
 
 
@@ -447,7 +454,7 @@ operations.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  17.201 seconds)
+   **Total running time of the script:** ( 1 minutes  24.873 seconds)
 
 
 .. _sphx_glr_download_tutorial_auto_scheduler_matmul_x86.py:
diff --git a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
index 35ca543b20..7bc02ae8ec 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -454,16 +454,16 @@ reduce variance, we take 5 measurements and average them.
     waiting for device...
     device available
     Get devices for measurement successfully!
-    No: 1   GFLOPS: 11.15/11.15     result: MeasureResult(costs=(0.024064627999999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6342036724090576, timestamp=1673476139.7607741)       [('tile_y', [-1, 2]), ('tile_x', [-1, 256])],None,81
-    No: 2   GFLOPS: 9.12/11.15      result: MeasureResult(costs=(0.0294418456,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7561562061309814, timestamp=1673476140.4886572)       [('tile_y', [-1, 16]), ('tile_x', [-1, 32])],None,54
-    No: 3   GFLOPS: 11.38/11.38     result: MeasureResult(costs=(0.023594366999999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6302731037139893, timestamp=1673476141.9188337)       [('tile_y', [-1, 256]), ('tile_x', [-1, 256])],None,88
-    No: 4   GFLOPS: 4.16/11.38      result: MeasureResult(costs=(0.06450905479999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2637012004852295, timestamp=1673476143.9887803)        [('tile_y', [-1, 16]), ('tile_x', [-1, 16])],None,44
-    No: 5   GFLOPS: 11.82/11.82     result: MeasureResult(costs=(0.0227151072,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6201920509338379, timestamp=1673476145.52235) [('tile_y', [-1, 32]), ('tile_x', [-1, 256])],None,85
-    No: 6   GFLOPS: 2.52/11.82      result: MeasureResult(costs=(0.1066255972,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9471800327301025, timestamp=1673476147.4821541)       [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
-    No: 7   GFLOPS: 3.68/11.82      result: MeasureResult(costs=(0.0729709884,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4184584617614746, timestamp=1673476148.909891)        [('tile_y', [-1, 128]), ('tile_x', [-1, 16])],None,47
-    No: 8   GFLOPS: 2.82/11.82      result: MeasureResult(costs=(0.09518413960000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7624521255493164, timestamp=1673476150.6870484)        [('tile_y', [-1, 16]), ('tile_x', [-1, 4])],None,24
-    No: 9   GFLOPS: 11.10/11.82     result: MeasureResult(costs=(0.0241869776,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6018955707550049, timestamp=1673476151.4044724)       [('tile_y', [-1, 256]), ('tile_x', [-1, 32])],None,58
-    No: 10  GFLOPS: 1.73/11.82      result: MeasureResult(costs=(0.1547198674,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.6894116401672363, timestamp=1673476154.1329095)       [('tile_y', [-1, 16]), ('tile_x', [-1, 2])],None,14
+    No: 1   GFLOPS: 13.37/13.37     result: MeasureResult(costs=(0.0200726826,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6037111282348633, timestamp=1673500712.3041794)       [('tile_y', [-1, 16]), ('tile_x', [-1, 512])],None,94
+    No: 2   GFLOPS: 0.51/13.37      result: MeasureResult(costs=(0.529461037,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.707215070724487, timestamp=1673500721.799314)  [('tile_y', [-1, 128]), ('tile_x', [-1, 1])],None,7
+    No: 3   GFLOPS: 3.63/13.37      result: MeasureResult(costs=(0.07401939119999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4249110221862793, timestamp=1673500723.9996781)        [('tile_y', [-1, 16]), ('tile_x', [-1, 8])],None,34
+    No: 4   GFLOPS: 1.55/13.37      result: MeasureResult(costs=(0.1726361118,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.9892475605010986, timestamp=1673500727.0241518)       [('tile_y', [-1, 8]), ('tile_x', [-1, 1])],None,3
+    No: 5   GFLOPS: 8.90/13.37      result: MeasureResult(costs=(0.030145890200000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7194933891296387, timestamp=1673500728.118538)        [('tile_y', [-1, 2]), ('tile_x', [-1, 64])],None,61
+    No: 6   GFLOPS: 2.48/13.37      result: MeasureResult(costs=(0.1082541314,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.979374885559082, timestamp=1673500730.1125202)        [('tile_y', [-1, 512]), ('tile_x', [-1, 16])],None,49
+    No: 7   GFLOPS: 14.75/14.75     result: MeasureResult(costs=(0.0182011378,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7912435531616211, timestamp=1673500731.4248652)       [('tile_y', [-1, 64]), ('tile_x', [-1, 64])],None,66
+    No: 8   GFLOPS: 12.45/14.75     result: MeasureResult(costs=(0.0215555188,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5765843391418457, timestamp=1673500732.0301383)       [('tile_y', [-1, 2]), ('tile_x', [-1, 512])],None,91
+    No: 9   GFLOPS: 13.24/14.75     result: MeasureResult(costs=(0.0202767398,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5358881950378418, timestamp=1673500732.7189577)       [('tile_y', [-1, 256]), ('tile_x', [-1, 64])],None,68
+    No: 10  GFLOPS: 10.36/14.75     result: MeasureResult(costs=(0.025921866199999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6617317199707031, timestamp=1673500733.3824596)       [('tile_y', [-1, 8]), ('tile_x', [-1, 64])],None,63
 
 
 
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 81606432da..60dfc1f503 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -324,7 +324,7 @@ standard deviation.
 
  .. code-block:: none
 
-    {'mean': 521.8501570299998, 'median': 521.9684494999967, 'std': 1.6557362052756646}
+    {'mean': 517.3716070399997, 'median': 517.7485770500027, 'std': 3.4011251652776395}
 
 
 
@@ -558,30 +558,31 @@ 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:   18.91/  18.91 GFLOPS | Progress: (4/20) | 8.83 s
    [Task  1/25]  Current/Best:   19.08/  19.08 GFLOPS | Progress: (8/20) | 12.92 s
    [Task  1/25]  Current/Best:    3.18/  19.08 GFLOPS | Progress: (12/20) | 15.93 s
    [Task  1/25]  Current/Best:    3.43/  19.08 GFLOPS | Progress: (16/20) | 18.88 s
    [Task  1/25]  Current/Best:    8.60/  21.78 GFLOPS | Progress: (20/20) | 22.26 s Done.
-
    [Task  2/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  2/25]  Current/Best:   11.95/  12.56 GFLOPS | Progress: (4/20) | 3.32 s
    [Task  2/25]  Current/Best:    3.75/  12.56 GFLOPS | Progress: (8/20) | 5.34 s
    [Task  2/25]  Current/Best:   19.81/  21.22 GFLOPS | Progress: (12/20) | 7.16 s
    [Task  2/25]  Current/Best:    6.51/  21.22 GFLOPS | Progress: (16/20) | 9.19 s
    [Task  2/25]  Current/Best:    9.95/  21.22 GFLOPS | Progress: (20/20) | 10.86 s Done.
-
    [Task  3/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  3/25]  Current/Best:    9.78/  13.64 GFLOPS | Progress: (4/20) | 4.41 s
    [Task  3/25]  Current/Best:   12.39/  13.64 GFLOPS | Progress: (8/20) | 7.65 s
    [Task  3/25]  Current/Best:    7.59/  22.62 GFLOPS | Progress: (12/20) | 10.94 s
    [Task  3/25]  Current/Best:   14.75/  22.62 GFLOPS | Progress: (16/20) | 13.22 s
    [Task  3/25]  Current/Best:   15.75/  23.06 GFLOPS | Progress: (20/20) | 15.35 s Done.
-
    [Task  4/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  4/25]  Current/Best:    2.19/  22.19 GFLOPS | Progress: (4/20) | 7.29 s
    [Task  4/25]  Current/Best:    4.31/  22.19 GFLOPS | Progress: (8/20) | 9.28 s
    [Task  4/25]  Current/Best:   10.83/  22.19 GFLOPS | Progress: (12/20) | 13.80 s
    [Task  4/25]  Current/Best:    6.10/  22.19 GFLOPS | Progress: (16/20) | 22.13 s
    [Task  4/25]  Current/Best:   12.68/  22.19 GFLOPS | Progress: (20/20) | 24.35 s Done.
-
    [Task  5/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  5/25]  Current/Best:   12.38/  15.24 GFLOPS | Progress: (4/20) | 4.07 s
    [Task  5/25]  Current/Best:    7.49/  15.24 GFLOPS | Progress: (8/20) | 6.39 s
    [Task  5/25]  Current/Best:    3.14/  15.24 GFLOPS | Progress: (12/20) | 9.47 s
    [Task  5/25]  Current/Best:    6.03/  17.78 GFLOPS | Progress: (16/20) | 11.65 s
    [Task  5/25]  Current/Best:   15.70/  17.78 GFLOPS | Progress: (20/20) | 13.61 s Done.
-
    [Task  6/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  6/25]  Current/Best:    9.94/  17.29 GFLOPS | Progress: (4/20) | 5.12 s
    [Task  6/25]  Current/Best:    5.01/  22.57 GFLOPS | Progress: (8/20) | 7.65 s
    [Task  6/25]  Current/Best:   18.87/  22.57 GFLOPS | Progress: (12/20) | 10.20 s
    [Task  6/25]  Current/Best:   14.45/  22.57 GFLOPS | Progress: (16/20) | 13.73 s
    [Task  6/25]  Current/Best:   18.14/  22.57 GFLOPS | Progress: (20/20) | 16.04 s Done.
-
    [Task  7/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  7/25]  Current/Best:   15.61/  15.61 GFLOPS | Progress: (4/20) | 4.22 s
    [Task  7/25]  Current/Best:    6.03/  18.10 GFLOPS | Progress: (8/20) | 7.88 s
    [Task  7/25]  Current/Best:   13.07/  18.10 GFLOPS | Progress: (12/20) | 10.30 s
    [Task  7/25]  Current/Best:   15.40/  20.93 GFLOPS | Progress: (16/20) | 12.56 s
    [Task  7/25]  Current/Best:   17.08/  20.93 GFLOPS | Progress: (20/20) | 14.75 s Done.
-
    [Task  8/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  8/25]  Current/Best:    7.58/  18.95 GFLOPS | Progress: (4/20) | 9.69 s
    [Task  8/25]  Current/Best:   18.18/  18.95 GFLOPS | Progress: (8/20) | 13.33 s
    [Task  8/25]  Current/Best:   13.05/  18.95 GFLOPS | Progress: (12/20) | 15.90 s
    [Task  8/25]  Current/Best:   10.91/  18.95 GFLOPS | Progress: (16/20) | 22.14 s
    [Task  8/25]  Current/Best:   11.36/  18.95 GFLOPS | Progress: (20/20) | 27.23 s Done.
-
    [Task  9/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  9/25]  Current/Best:   11.95/  13.32 GFLOPS | Progress: (4/20) | 9.79 s
    [Task  9/25]  Current/Best:   16.01/  18.42 GFLOPS | Progress: (8/20) | 12.11 s
    [Task  9/25]  Current/Best:   11.33/  18.42 GFLOPS | Progress: (12/20) | 18.46 s
    [Task  9/25]  Current/Best:    5.24/  20.54 GFLOPS | Progress: (16/20) | 20.62 s
    [Task  9/25]  Current/Best:   11.64/  20.54 GFLOPS | Progress: (20/20) | 24.54 s Done.
-
    [Task 10/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 10/25]  Current/Best:   17.71/  17.71 GFLOPS | Progress: (4/20) | 4.13 s
    [Task 10/25]  Current/Best:    5.12/  17.71 GFLOPS | Progress: (8/20) | 6.11 s
    [Task 10/25]  Current/Best:    8.05/  17.71 GFLOPS | Progress: (12/20) | 8.59 s
    [Task 10/25]  Current/Best:   15.20/  17.71 GFLOPS | Progress: (16/20) | 10.53 s
    [Task 10/25]  Current/Best:   15.38/  17.71 GFLOPS | Progress: (20/20) | 12.39 s Done.
-
    [Task 11/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 11/25]  Current/Best:   12.69/  18.55 GFLOPS | Progress: (4/20) | 4.24 s
    [Task 11/25]  Current/Best:   21.12/  23.71 GFLOPS | Progress: (8/20) | 6.36 s
    [Task 11/25]  Current/Best:   12.07/  23.71 GFLOPS | Progress: (12/20) | 8.82 s
    [Task 11/25]  Current/Best:   18.41/  23.71 GFLOPS | Progress: (16/20) | 12.61 s
    [Task 11/25]  Current/Best:   15.38/  23.71 GFLOPS | Progress: (20/20) | 14.97 s Done.
-
    [Task 12/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 12/25]  Current/Best:   10.56/  11.60 GFLOPS | Progress: (4/20) | 5.51 s
    [Task 12/25]  Current/Best:   10.01/  12.86 GFLOPS | Progress: (8/20) | 10.64 s
    [Task 12/25]  Current/Best:   12.78/  21.95 GFLOPS | Progress: (12/20) | 13.17 s
    [Task 12/25]  Current/Best:   16.26/  21.95 GFLOPS | Progress: (16/20) | 16.64 s
    [Task 12/25]  Current/Best:    5.14/  21.95 GFLOPS | Progress: (20/20) | 22.71 s Done.
-
    [Task 13/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 13/25]  Current/Best:    9.72/  21.28 GFLOPS | Progress: (4/20) | 5.76 s
    [Task 13/25]  Current/Best:   12.91/  21.28 GFLOPS | Progress: (8/20) | 8.30 s
    [Task 13/25]  Current/Best:   17.09/  21.28 GFLOPS | Progress: (12/20) | 10.82 s
    [Task 13/25]  Current/Best:   19.72/  21.28 GFLOPS | Progress: (16/20) | 13.51 s
    [Task 13/25]  Current/Best:   16.59/  21.28 GFLOPS | Progress: (20/20) | 15.95 s Done.
-
    [Task 14/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 14/25]  Current/Best:   12.46/  18.55 GFLOPS | Progress: (4/20) | 4.08 s
    [Task 14/25]  Current/Best:    8.88/  18.55 GFLOPS | Progress: (8/20) | 9.43 s
    [Task 14/25]  Current/Best:   10.78/  18.55 GFLOPS | Progress: (12/20) | 15.53 s
    [Task 14/25]  Current/Best:   15.51/  18.55 GFLOPS | Progress: (16/20) | 18.19 s
    [Task 14/25]  Current/Best:   14.96/  18.55 GFLOPS | Progress: (20/20) | 20.53 s
    [Task 15/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 15/25]  Current/Best:   17.24/  21.78 GFLOPS | Progress: (4/20) | 5.03 s
    [Task 15/25]  Current/Best:    9.68/  22.03 GFLOPS | Progress: (8/20) | 9.44 s Done.
-
    [Task 15/25]  Current/Best:    6.74/  22.03 GFLOPS | Progress: (12/20) | 11.21 s
    [Task 15/25]  Current/Best:   12.31/  22.03 GFLOPS | Progress: (16/20) | 13.62 s
    [Task 15/25]  Current/Best:   18.99/  22.03 GFLOPS | Progress: (20/20) | 15.41 s Done.
-
    [Task 16/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 16/25]  Current/Best:   15.67/  19.35 GFLOPS | Progress: (4/20) | 3.45 s
    [Task 16/25]  Current/Best:   18.41/  19.35 GFLOPS | Progress: (8/20) | 5.15 s
    [Task 16/25]  Current/Best:   12.19/  19.35 GFLOPS | Progress: (12/20) | 7.50 s
    [Task 16/25]  Current/Best:    5.45/  20.52 GFLOPS | Progress: (16/20) | 9.29 s
    [Task 16/25]  Current/Best:   19.06/  20.52 GFLOPS | Progress: (20/20) | 13.00 s Done.
-
    [Task 17/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 17/25]  Current/Best:    6.11/  19.05 GFLOPS | Progress: (4/20) | 4.18 s
    [Task 17/25]  Current/Best:   19.91/  19.91 GFLOPS | Progress: (8/20) | 6.39 s
    [Task 17/25]  Current/Best:   11.29/  19.91 GFLOPS | Progress: (12/20) | 9.86 s
    [Task 17/25]  Current/Best:   18.99/  21.72 GFLOPS | Progress: (16/20) | 12.10 s
    [Task 17/25]  Current/Best:   22.16/  22.16 GFLOPS | Progress: (20/20) | 14.41 s Done.
-
    [Task 18/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 18/25]  Current/Best:    9.29/  18.79 GFLOPS | Progress: (4/20) | 5.57 s
    [Task 18/25]  Current/Best:   14.30/  18.79 GFLOPS | Progress: (8/20) | 9.37 s
    [Task 18/25]  Current/Best:   10.37/  18.79 GFLOPS | Progress: (12/20) | 14.10 s
    [Task 18/25]  Current/Best:    6.99/  20.09 GFLOPS | Progress: (16/20) | 16.34 s
    [Task 18/25]  Current/Best:   18.12/  20.09 GFLOPS | Progress: (20/20) | 18.53 s Done.
-
    [Task 19/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 19/25]  Current/Best:   19.39/  21.25 GFLOPS | Progress: (4/20) | 4.81 s
    [Task 19/25]  Current/Best:    5.27/  21.25 GFLOPS | Progress: (8/20) | 8.55 s
    [Task 19/25]  Current/Best:   17.33/  21.25 GFLOPS | Progress: (12/20) | 12.44 s
    [Task 19/25]  Current/Best:   18.92/  21.25 GFLOPS | Progress: (16/20) | 16.00 s
    [Task 19/25]  Current/Best:   11.89/  21.25 GFLOPS | Progress: (20/20) | 20.67 s Done.
-
    [Task 20/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 20/25]  Current/Best:   15.00/  15.00 GFLOPS | Progress: (4/20) | 4.21 s
    [Task 20/25]  Current/Best:   11.04/  15.00 GFLOPS | Progress: (8/20) | 9.07 s
    [Task 20/25]  Current/Best:   10.55/  16.52 GFLOPS | Progress: (12/20) | 14.67 s
    [Task 20/25]  Current/Best:   15.59/  16.55 GFLOPS | Progress: (16/20) | 17.87 s
    [Task 20/25]  Current/Best:   18.57/  18.57 GFLOPS | Progress: (20/20) | 21.53 s
    [Task 21/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 21/25]  Current/Best:    6.71/  16.63 GFLOPS | Progress: (4/20) | 4.84 s
    [Task 21/25]  Current/Best:    8.27/  18.80 GFLOPS | Progress: (8/20) | 7.05 s
    [Task 21/25]  Current/Best:   19.93/  19.93 GFLOPS | Progress: (12/20) | 8.64 s
    [Task 21/25]  Current/Best:    8.81/  19.93 GFLOPS | Progress: (16/20) | 10.74 s
    [Task 21/25]  Current/Best:    9.43/  19.93 GFLOPS | Progress: (20/20)
  | 12.52 s Done.
-
    [Task 22/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 22/25]  Current/Best:   13.76/  18.74 GFLOPS | Progress: (4/20) | 3.78 s
    [Task 22/25]  Current/Best:    9.94/  18.74 GFLOPS | Progress: (8/20) | 5.67 s
    [Task 22/25]  Current/Best:   14.99/  18.74 GFLOPS | Progress: (12/20) | 8.85 s
    [Task 22/25]  Current/Best:   17.22/  18.74 GFLOPS | Progress: (16/20) | 10.45 s
    [Task 22/25]  Current/Best:   17.27/  18.74 GFLOPS | Progress: (20/20) | 12.28 s Done.
-
    [Task 23/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 23/25]  Current/Best:   18.74/  18.74 GFLOPS | Progress: (4/20) | 5.65 s
    [Task 23/25]  Current/Best:   17.92/  18.74 GFLOPS | Progress: (8/20) | 8.68 s
    [Task 23/25]  Current/Best:   19.32/  19.56 GFLOPS | Progress: (12/20) | 10.83 s
    [Task 23/25]  Current/Best:   11.69/  19.56 GFLOPS | Progress: (16/20) | 13.69 s
    [Task 23/25]  Current/Best:   17.79/  19.56 GFLOPS | Progress: (20/20) | 16.34 s Done.
-
    [Task 24/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 24/25]  Current/Best:    3.26/   8.20 GFLOPS | Progress: (4/20) | 12.83 s Done.
-
    [Task 24/25]  Current/Best:    3.56/   9.78 GFLOPS | Progress: (8/20) | 19.15 s
    [Task 24/25]  Current/Best:   10.03/  10.03 GFLOPS | Progress: (12/20) | 22.72 s
    [Task 24/25]  Current/Best:    7.64/  10.03 GFLOPS | Progress: (16/20) | 26.39 s
    [Task 24/25]  Current/Best:    3.80/  10.03 GFLOPS | Progress: (20/20) | 37.07 s
    [Task 25/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 25/25]  Current/Best:    8.45/   8.45 GFLOPS | Progress: (4/20) | 14.07 s
    [Task 25/25]  Current/Best:    2.77/   8.87 GFLOPS | Progress: (8/20) | 25.02 s
    [Task 25/25]  Current/Best:    3.48/   8.87 GFLOPS | Progress: (12/20) | 27.20 s
    [Task 25/25]  Current/Best:    9.05/   9.05 GFLOPS | Progress: (16/20) | 38.16 s
    [Task 25/25]  Current/Best:    5.92/   9.05 GFLOPS | Progress: (20/20) | 49.09 s
+
    [Task  1/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  1/25]  Current/Best:    7.42/  17.89 GFLOPS | Progress: (4/20) | 8.78 s
    [Task  1/25]  Current/Best:   10.94/  23.57 GFLOPS | Progress: (8/20) | 11.84 s
    [Task  1/25]  Current/Best:    8.44/  23.57 GFLOPS | Progress: (12/20) | 15.91 s
    [Task  1/25]  Current/Best:   23.77/  23.77 GFLOPS | Progress: (16/20) | 18.74 s
    [Task  1/25]  Current/Best:    1.92/  23.77 GFLOPS | Progress: (20/20) | 23.24 s Done.
+
    [Task  2/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  2/25]  Current/Best:   12.80/  15.85 GFLOPS | Progress: (4/20) | 3.85 s
    [Task  2/25]  Current/Best:   14.86/  18.41 GFLOPS | Progress: (8/20) | 6.84 s
    [Task  2/25]  Current/Best:    8.27/  18.48 GFLOPS | Progress: (12/20) | 8.37 s
    [Task  2/25]  Current/Best:   13.36/  21.06 GFLOPS | Progress: (16/20) | 10.26 s
    [Task  2/25]  Current/Best:    9.46/  21.06 GFLOPS | Progress: (20/20) | 12.21 s Done.
+
    [Task  3/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  3/25]  Current/Best:   14.38/  16.45 GFLOPS | Progress: (4/20) | 4.22 s
    [Task  3/25]  Current/Best:   17.76/  17.94 GFLOPS | Progress: (8/20) | 7.07 s
    [Task  3/25]  Current/Best:   15.34/  17.94 GFLOPS | Progress: (12/20) | 10.58 s
    [Task  3/25]  Current/Best:   16.16/  17.94 GFLOPS | Progress: (16/20) | 12.86 s
    [Task  3/25]  Current/Best:    8.48/  17.94 GFLOPS | Progress: (20/20) | 16.68 s Done.
+
    [Task  4/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  4/25]  Current/Best:   12.92/  12.92 GFLOPS | Progress: (4/20) | 7.40 s
    [Task  4/25]  Current/Best:   12.22/  12.92 GFLOPS | Progress: (8/20) | 10.29 s
    [Task  4/25]  Current/Best:   15.22/  20.62 GFLOPS | Progress: (12/20) | 12.48 s
    [Task  4/25]  Current/Best:    9.49/  20.62 GFLOPS | Progress: (16/20) | 18.60 s
    [Task  4/25]  Current/Best:    6.47/  20.62 GFLOPS | Progress: (20/20) | 23.47 s Done.
+
    [Task  5/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  5/25]  Current/Best:   14.02/  14.02 GFLOPS | Progress: (4/20) | 5.16 s
    [Task  5/25]  Current/Best:   11.84/  17.31 GFLOPS | Progress: (8/20) | 7.59 s
    [Task  5/25]  Current/Best:   11.92/  17.45 GFLOPS | Progress: (12/20) | 9.47 s
    [Task  5/25]  Current/Best:   13.37/  17.45 GFLOPS | Progress: (16/20) | 11.36 s
    [Task  5/25]  Current/Best:   11.75/  20.45 GFLOPS | Progress: (20/20) | 13.76 s Done.
+
    [Task  6/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  6/25]  Current/Best:   15.36/  21.82 GFLOPS | Progress: (4/20) | 3.83 s
    [Task  6/25]  Current/Best:    5.99/  21.82 GFLOPS | Progress: (8/20) | 6.96 s
    [Task  6/25]  Current/Best:   12.06/  22.61 GFLOPS | Progress: (12/20) | 10.39 s
    [Task  6/25]  Current/Best:   11.96/  22.61 GFLOPS | Progress: (16/20) | 13.71 s
    [Task  6/25]  Current/Best:    3.95/  22.61 GFLOPS | Progress: (20/20) | 17.45 s Done.
+
    [Task  7/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  7/25]  Current/Best:   18.26/  18.26 GFLOPS | Progress: (4/20) | 4.03 s
    [Task  7/25]  Current/Best:   12.40/  20.54 GFLOPS | Progress: (8/20) | 7.06 s
    [Task  7/25]  Current/Best:   13.91/  22.02 GFLOPS | Progress: (12/20) | 9.23 s
    [Task  7/25]  Current/Best:   11.92/  22.02 GFLOPS | Progress: (16/20) | 11.19 s
    [Task  7/25]  Current/Best:   19.27/  22.02 GFLOPS | Progress: (20/20) | 15.00 s Done.
+
    [Task  8/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  8/25]  Current/Best:   15.90/  15.90 GFLOPS | Progress: (4/20) | 7.10 s
    [Task  8/25]  Current/Best:   10.88/  15.90 GFLOPS | Progress: (8/20) | 18.74 s
    [Task  8/25]  Current/Best:   13.66/  15.90 GFLOPS | Progress: (12/20) | 25.13 s
    [Task  8/25]  Current/Best:   14.98/  15.90 GFLOPS | Progress: (16/20) | 27.48 s
    [Task  8/25]  Current/Best:    8.04/  15.90 GFLOPS | Progress: (20/20) | 31.60 s Done.
+
    [Task  9/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  9/25]  Current/Best:   10.22/  17.40 GFLOPS | Progress: (4/20) | 8.85 s
    [Task  9/25]  Current/Best:    6.49/  18.80 GFLOPS | Progress: (8/20) | 10.88 s
    [Task  9/25]  Current/Best:   14.11/  18.80 GFLOPS | Progress: (12/20) | 14.32 s
    [Task  9/25]  Current/Best:   15.87/  18.80 GFLOPS | Progress: (16/20) | 21.38 s
    [Task  9/25]  Current/Best:    8.39/  19.47 GFLOPS | Progress: (20/20) | 23.78 s Done.
+
    [Task 10/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 10/25]  Current/Best:   15.08/  20.15 GFLOPS | Progress: (4/20) | 3.78 s
    [Task 10/25]  Current/Best:   17.70/  20.15 GFLOPS | Progress: (8/20) | 5.85 s
    [Task 10/25]  Current/Best:    5.28/  20.15 GFLOPS | Progress: (12/20) | 7.70 s
    [Task 10/25]  Current/Best:    1.61/  22.08 GFLOPS | Progress: (16/20) | 9.77 s
    [Task 10/25]  Current/Best:   10.01/  22.08 GFLOPS | Progress: (20/20) | 12.17 s Done.
+
    [Task 11/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 11/25]  Current/Best:   17.68/  17.76 GFLOPS | Progress: (4/20) | 4.22 s
    [Task 11/25]  Current/Best:   13.34/  20.38 GFLOPS | Progress: (8/20) | 6.52 s
    [Task 11/25]  Current/Best:   17.76/  22.41 GFLOPS | Progress: (12/20) | 8.67 s
    [Task 11/25]  Current/Best:   14.19/  22.41 GFLOPS | Progress: (16/20) | 10.96 s
    [Task 11/25]  Current/Best:    3.13/  22.41 GFLOPS | Progress: (20/20) | 13.59 s Done.
+
    [Task 12/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 12/25]  Current/Best:   10.74/  17.51 GFLOPS | Progress: (4/20) | 4.37 s
    [Task 12/25]  Current/Best:   11.24/  18.54 GFLOPS | Progress: (8/20) | 8.57 s
    [Task 12/25]  Current/Best:   11.29/  18.54 GFLOPS | Progress: (12/20) | 11.49 s
    [Task 12/25]  Current/Best:   11.64/  18.54 GFLOPS | Progress: (16/20) | 13.73 s
    [Task 12/25]  Current/Best:   19.34/  19.34 GFLOPS | Progress: (20/20) | 20.15 s Done.
+
    [Task 13/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 13/25]  Current/Best:   16.04/  16.04 GFLOPS | Progress: (4/20) | 5.39 s
    [Task 13/25]  Current/Best:   11.68/  20.24 GFLOPS | Progress: (8/20) | 8.88 s
    [Task 13/25]  Current/Best:   18.03/  20.24 GFLOPS | Progress: (12/20) | 12.31 s
    [Task 13/25]  Current/Best:    7.55/  20.24 GFLOPS | Progress: (16/20) | 15.23 s
    [Task 13/25]  Current/Best:   11.75/  21.76 GFLOPS | Progress: (20/20) | 18.50 s Done.
+
    [Task 14/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 14/25]  Current/Best:    5.65/   7.98 GFLOPS | Progress: (4/20) | 4.98 s
    [Task 14/25]  Current/Best:    6.26/  15.35 GFLOPS | Progress: (8/20) | 8.17 s
    [Task 14/25]  Current/Best:    9.00/  15.35 GFLOPS | Progress: (12/20) | 11.72 s
    [Task 14/25]  Current/Best:   15.72/  19.59 GFLOPS | Progress: (16/20) | 14.50 s
    [Task 14/25]  Current/Best:    5.85/  19.59 GFLOPS | Progress: (20/20) | 17.14 s
    [Task 15/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 15/25]  Current/Best:    6.68/  15.65 GFLOPS | Progress: (4/20) | 4.37 s
    [Task 15/25]  Current/Best:   22.58/  22.58 GFLOPS | Progress: (8/20) | 5.84 s
    [Task 15/25]  Current/Best:   14.85/  22.58 GFLOPS | Progress: (12/20) | 8.41 s
    [Task 15/25]  Current/Best:   10.11/  22.58 GFLOPS | Progress: (16/20) | 11.98 s
    [Task 15/25]  Current/Best:   13.00/  22.58 GFLOPS | Progress: (20/20)
  | 14.37 s
    [Task 16/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+     Done.
+
    [Task 16/25]  Current/Best:   12.96/  12.96 GFLOPS | Progress: (4/20) | 4.99 s
    [Task 16/25]  Current/Best:    9.46/  12.96 GFLOPS | Progress: (8/20) | 7.94 s
    [Task 16/25]  Current/Best:   10.58/  18.97 GFLOPS | Progress: (12/20) | 10.65 s
    [Task 16/25]  Current/Best:   11.65/  18.97 GFLOPS | Progress: (16/20) | 13.39 s
    [Task 16/25]  Current/Best:   13.58/  18.97 GFLOPS | Progress: (20/20) | 15.39 s Done.
+
    [Task 17/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 17/25]  Current/Best:   18.26/  18.26 GFLOPS | Progress: (4/20) | 4.37 s
    [Task 17/25]  Current/Best:   22.27/  22.27 GFLOPS | Progress: (8/20) | 6.69 s
    [Task 17/25]  Current/Best:    9.08/  23.75 GFLOPS | Progress: (12/20) | 9.25 s
    [Task 17/25]  Current/Best:   11.93/  23.75 GFLOPS | Progress: (16/20) | 11.45 s
    [Task 17/25]  Current/Best:    9.66/  23.75 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:    4.24/  15.78 GFLOPS | Progress: (4/20) | 5.99 s
    [Task 18/25]  Current/Best:    3.09/  16.61 GFLOPS | Progress: (8/20) | 10.46 s
    [Task 18/25]  Current/Best:   19.16/  19.16 GFLOPS | Progress: (12/20) | 13.00 s
    [Task 18/25]  Current/Best:   18.41/  19.16 GFLOPS | Progress: (16/20) | 15.36 s
    [Task 18/25]  Current/Best:    3.11/  19.16 GFLOPS | Progress: (20/20) | 19.59 s Done.
+
    [Task 19/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 19/25]  Current/Best:   11.96/  18.03 GFLOPS | Progress: (4/20) | 5.05 s
    [Task 19/25]  Current/Best:    2.56/  18.03 GFLOPS | Progress: (8/20) | 9.73 s
    [Task 19/25]  Current/Best:   11.08/  18.03 GFLOPS | Progress: (12/20) | 13.60 s
    [Task 19/25]  Current/Best:   19.02/  19.02 GFLOPS | Progress: (16/20) | 17.79 s
    [Task 19/25]  Current/Best:   13.15/  19.02 GFLOPS | Progress: (20/20) | 21.73 s Done.
+
    [Task 20/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 20/25]  Current/Best:    6.39/  17.86 GFLOPS | Progress: (4/20) | 4.16 s
    [Task 20/25]  Current/Best:   11.04/  19.54 GFLOPS | Progress: (8/20) | 8.01 s
    [Task 20/25]  Current/Best:   17.57/  19.54 GFLOPS | Progress: (12/20) | 10.32 s
    [Task 20/25]  Current/Best:   13.23/  19.54 GFLOPS | Progress: (16/20) | 14.03 s
    [Task 20/25]  Current/Best:    5.12/  19.54 GFLOPS | Progress: (20/20) | 16.46 s
    [Task 21/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 21/25]  Current/Best:   13.56/  14.43 GFLOPS | Progress: (4/20) | 4.02 s
    [Task 21/25]  Current/Best:   16.47/  16.47 GFLOPS | Progress: (8/20) | 6.21 s
    [Task 21/25]  Current/Best:    9.16/  17.43 GFLOPS | Progress: (12/20) | 9.39 s
    [Task 21/25]  Current/Best:    9.88/  17.43 GFLOPS | Progress: (16/20) | 12.01 s
    [Task 21/25]  Current/Best:   14.17/  17.43 GFLOPS | Progress: (20/20)
  | 13.25 s
    [Task 22/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+     Done.
+
    [Task 22/25]  Current/Best:    8.88/  21.29 GFLOPS | Progress: (4/20) | 5.64 s
    [Task 22/25]  Current/Best:   21.33/  21.33 GFLOPS | Progress: (8/20) | 7.43 s
    [Task 22/25]  Current/Best:   16.35/  21.33 GFLOPS | Progress: (12/20) | 9.63 s
    [Task 22/25]  Current/Best:   14.10/  21.33 GFLOPS | Progress: (16/20) | 12.06 s
    [Task 22/25]  Current/Best:   20.26/  21.33 GFLOPS | Progress: (20/20) | 13.82 s Done.
+
    [Task 23/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 23/25]  Current/Best:   11.27/  20.10 GFLOPS | Progress: (4/20) | 4.03 s
    [Task 23/25]  Current/Best:   12.13/  20.10 GFLOPS | Progress: (8/20) | 7.69 s
    [Task 23/25]  Current/Best:   19.31/  20.10 GFLOPS | Progress: (12/20) | 11.05 s
    [Task 23/25]  Current/Best:   13.64/  20.10 GFLOPS | Progress: (16/20) | 14.03 s
    [Task 23/25]  Current/Best:   19.74/  20.27 GFLOPS | Progress: (20/20) | 17.21 s Done.
+
    [Task 24/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 24/25]  Current/Best:    3.02/   9.84 GFLOPS | Progress: (4/20) | 12.46 s
    [Task 24/25]  Current/Best:    9.48/   9.84 GFLOPS | Progress: (8/20) | 24.25 s
    [Task 24/25]  Current/Best:    8.88/   9.84 GFLOPS | Progress: (12/20) | 28.33 s
    [Task 24/25]  Current/Best:    5.98/   9.84 GFLOPS | Progress: (16/20) | 38.99 s
    [Task 24/25]  Current/Best:    0.88/   9.84 GFLOPS | Progress: (20/20) | 49.97 s
    [Task 25/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
    [Task 25/25]  Current/Best:    9.34/   9.34 GFLOPS | Progress: (4/20) | 4.21 s
    [Task 25/25]  Current/Best:    2.56/   9.34 GFLOPS | Progress: (8/20) | 7.17 s
    [Task 25/25]  Current/Best:    1.55/   9.34 GFLOPS | Progress: (12/20) | 18.15 s
    [Task 25/25]  Current/Best:    3.04/   9.34 GFLOPS | Progress: (16/20) | 29.12 s
    [Task 25/25]  Current/Best:    6.55/   9.34 GFLOPS | Progress: (20/20) | 32.30 s
 
 
 
@@ -735,8 +736,8 @@ improvement in comparing the optimized model to the unoptimized model.
 
  .. code-block:: none
 
-    optimized: {'mean': 410.29078650999963, 'median': 409.65584635000596, 'std': 2.818926327091351}
-    unoptimized: {'mean': 521.8501570299998, 'median': 521.9684494999967, 'std': 1.6557362052756646}
+    optimized: {'mean': 422.4226451399977, 'median': 422.28647095000724, 'std': 0.712730470689489}
+    unoptimized: {'mean': 517.3716070399997, 'median': 517.7485770500027, 'std': 3.4011251652776395}
 
 
 
@@ -759,7 +760,7 @@ profiling/benchmarking.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 11 minutes  39.629 seconds)
+   **Total running time of the script:** ( 11 minutes  35.793 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 be20099041..7dd31835f3 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -274,7 +274,7 @@ device and returns the measured cost. Network overhead is excluded.
 
  .. code-block:: none
 
-    1.266e-07 secs/op
+    1.262e-07 secs/op
 
 
 
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index d041a5b374..138b16fc46 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -264,7 +264,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
 
  .. code-block:: none
 
-    [stage(a, placeholder(a, 0x254c1840)), stage(b, placeholder(b, 0x22195ab0)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(mi [...]
+    [stage(a, placeholder(a, 0x22959e90)), stage(b, placeholder(b, 0x22cab760)), 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 45db7bd403..89e0f9ff5c 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,32 +5,32 @@
 
 Computation times
 =================
-**14:56.041** total execution time for **tutorial** files:
+**15:02.789** total execution time for **tutorial** files:
 
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)                 | 11:39.629 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)                 | 11:35.793 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:17.201 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:24.873 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)     | 01:03.190 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)     | 00:59.771 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)                 | 00:34.267 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)                 | 00:33.802 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)               | 00:19.401 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)               | 00:26.158 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)       | 00:01.332 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)       | 00:01.395 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)                               | 00:00.830 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)                               | 00:00.819 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.182 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.169 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``)                           | 00:00.006 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``)                                             | 00:00.002 | 0.0 MB |
-+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_install.py` (``install.py``)                                     | 00:00.001 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``)                                             | 00:00.001 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``)   | 00:00.001 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_tutorial_install.py` (``install.py``)                                     | 00:00.001 | 0.0 MB |
++------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``)                             | 00:00.001 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 040b65764f..c3902563d9 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -298,7 +298,7 @@ helper function to run a profile of the TVM generated code.
 
  .. code-block:: none
 
-    Numpy running time: 0.000008
+    Numpy running time: 0.000007
     naive: 0.000007
 
 
@@ -397,7 +397,7 @@ compile and run this new schedule with the parallel operation applied:
 
  .. code-block:: none
 
-    parallel: 0.000008
+    parallel: 0.000007
 
 
 
@@ -503,10 +503,10 @@ We can now compare the different schedules
  .. code-block:: none
 
                 Operator                  Timing             Performance
-                   numpy    7.566829999632319e-06                    1.0
-                   naive              6.7772e-06      0.8956458649565686
-                parallel              8.1468e-06      1.0766463631924943
-                  vector             2.46977e-05      3.2639427608655263
+                   numpy    6.88419000198337e-06                     1.0
+                   naive              6.6813e-06       0.970528122854698
+                parallel              7.2451e-06      1.0524259205386037
+                  vector             2.46603e-05       3.582164349457996
 
 
 
@@ -927,7 +927,7 @@ matrix multiplication.
 
  .. code-block:: none
 
-    Numpy running time: 0.019046
+    Numpy running time: 0.018542
 
 
 
@@ -985,7 +985,7 @@ optimizations.
 
  .. code-block:: none
 
-    none: 3.544757
+    none: 3.311629
 
 
 
@@ -1087,7 +1087,7 @@ schedule.
 
  .. code-block:: none
 
-    blocking: 0.316453
+    blocking: 0.294998
 
 
 
@@ -1182,7 +1182,7 @@ already cache friendly from our previous optimizations.
 
  .. code-block:: none
 
-    vectorization: 0.349106
+    vectorization: 0.338305
     @main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
       attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
       buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1255,7 +1255,7 @@ more cache friendly.
 
  .. code-block:: none
 
-    loop permutation: 0.118895
+    loop permutation: 0.118767
     @main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
       attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
       buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1353,7 +1353,7 @@ optimized schedule.
 
  .. code-block:: none
 
-    array packing: 0.108927
+    array packing: 0.109970
     @main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
       attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
       buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1445,7 +1445,7 @@ to `C` when all the block results are ready.
 
  .. code-block:: none
 
-    block caching: 0.110840
+    block caching: 0.111164
     @main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
       attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
       buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1530,7 +1530,7 @@ of thread-level parallelization.
 
  .. code-block:: none
 
-    parallelization: 0.146037
+    parallelization: 0.146851
     @main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
       attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
       buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1610,13 +1610,13 @@ working, we can compare the results.
  .. code-block:: none
 
                 Operator                  Timing             Performance
-                    none      3.5447574942999998                     1.0
-                blocking            0.3164534302     0.08927364726892031
-           vectorization     0.34910588579999996     0.09848512524802196
-        loop permutation     0.11889488299999999      0.0335410484895466
-           array packing            0.1089274428     0.03072916637461272
-           block caching             0.110840491     0.03126885017613545
-         parallelization            0.1460370829    0.041198046166720535
+                    none      3.3116291861000002                     1.0
+                blocking            0.2949983061     0.08907951027192451
+           vectorization     0.33830494629999996     0.10215665078686267
+        loop permutation     0.11876672930000001     0.03586353502333629
+           array packing     0.10996959549999999     0.03320709817439061
+           block caching     0.11116439390000002     0.03356788687773186
+         parallelization            0.1468511693    0.044344085961188766
 
 
 
@@ -1656,11 +1656,6 @@ operations with tunable parameters that allows you to automatically optimize
 the computation for specific platforms.
 
 
-.. rst-class:: sphx-glr-timing
-
-   **Total running time of the script:** ( 1 minutes  3.190 seconds)
-
-
 .. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
 
 .. only:: html
diff --git a/docs/commit_hash b/docs/commit_hash
index b05927506e..1fc17c1585 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-f71841a199f747378b195020c8ec36ba652d547c
+079876ed5412e7f8beb4c8e82248cca461781ee2
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index ac4d693982..4cad2594af 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -585,7 +585,7 @@ class:[&#39;truck 0.9266&#39;] left:471 top:83 right:689 bottom:169
 class:[&#39;bicycle 0.9984&#39;] left:111 top:113 right:577 bottom:447
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  12.301 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  9.621 seconds)</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-darknet-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/7716f96385bd5abb6e822041e285be54/from_darknet.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_darknet.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_keras.html b/docs/how_to/compile_models/from_keras.html
index 0c9b4b3a32..3f1009ad14 100644
--- a/docs/how_to/compile_models/from_keras.html
+++ b/docs/how_to/compile_models/from_keras.html
@@ -506,7 +506,7 @@ Tensorflow is also required since it’s used as the default backend of keras.</
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Relay top-1 id: 285, class name: Egyptian cat
 
 1/1 [==============================] - ETA: 0s
-1/1 [==============================] - 1s 976ms/step
+1/1 [==============================] - 1s 956ms/step
 Keras top-1 id: 285, class name: Egyptian cat
 </pre></div>
 </div>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 5a8ddb362a..929f7fae53 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -439,7 +439,7 @@
 <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;x&quot;</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#tuple" title="builtins.tuple" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">x</span><span class="o">.</span><span class="n">shape</span></a><span class="p">)</span>
 </pre></div>
 </div>
-<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip57274787-008f-47be-ad9d-620e897c12fe from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipebcec47a-9d37-4a89-a9f8-ed9e09b03c8f 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 d81925435b..b2c6d76fc5 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -449,16 +449,14 @@ Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdo
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: &quot;https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip&quot; to /workspace/.oneflow/flowvision_cache/resnet18.zip
 
   0%|          | 0.00/41.5M [00:00&lt;?, ?B/s]
- 15%|#5        | 6.33M/41.5M [00:00&lt;00:00, 46.7MB/s]
- 26%|##6       | 10.8M/41.5M [00:00&lt;00:00, 46.4MB/s]
- 37%|###6      | 15.2M/41.5M [00:00&lt;00:00, 43.4MB/s]
- 47%|####6     | 19.3M/41.5M [00:00&lt;00:00, 41.8MB/s]
- 56%|#####6    | 23.3M/41.5M [00:00&lt;00:00, 40.2MB/s]
- 65%|######5   | 27.2M/41.5M [00:00&lt;00:00, 37.7MB/s]
- 77%|#######7  | 32.0M/41.5M [00:00&lt;00:00, 41.0MB/s]
- 87%|########6 | 36.0M/41.5M [00:00&lt;00:00, 41.4MB/s]
- 96%|#########6| 40.0M/41.5M [00:01&lt;00:00, 30.2MB/s]
-100%|##########| 41.5M/41.5M [00:01&lt;00:00, 38.1MB/s]
+ 15%|#5        | 6.33M/41.5M [00:00&lt;00:00, 39.3MB/s]
+ 24%|##4       | 10.1M/41.5M [00:00&lt;00:00, 35.3MB/s]
+ 39%|###8      | 16.0M/41.5M [00:00&lt;00:00, 43.2MB/s]
+ 58%|#####7    | 24.0M/41.5M [00:00&lt;00:00, 49.2MB/s]
+ 69%|######9   | 28.7M/41.5M [00:00&lt;00:00, 45.9MB/s]
+ 82%|########2 | 34.1M/41.5M [00:00&lt;00:00, 45.0MB/s]
+ 96%|#########6| 40.0M/41.5M [00:00&lt;00:00, 45.1MB/s]
+100%|##########| 41.5M/41.5M [00:00&lt;00:00, 45.8MB/s]
 </pre></div>
 </div>
 </div>
diff --git a/docs/how_to/compile_models/from_onnx.html b/docs/how_to/compile_models/from_onnx.html
index adbff82c67..7347ede42b 100644
--- a/docs/how_to/compile_models/from_onnx.html
+++ b/docs/how_to/compile_models/from_onnx.html
@@ -460,7 +460,7 @@ provides a static definition of the input size.</p>
     <span class="p">)</span><span class="o">.</span><span class="n">evaluate</span><span class="p">()</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/relay/frontend/onnx.py:6577: UserWarning: Mismatched attribute type in &#39; : kernel_shape&#39;
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/relay/frontend/onnx.py:6689: UserWarning: Mismatched attribute type in &#39; : kernel_shape&#39;
 
 ==&gt; Context: Bad node spec for node. Name:  OpType: Conv
   warnings.warn(str(e))
diff --git a/docs/how_to/compile_models/from_pytorch.html b/docs/how_to/compile_models/from_pytorch.html
index 311e931119..3e6303d1eb 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -432,12 +432,10 @@ be unstable.</p>
 Downloading: &quot;https://download.pytorch.org/models/resnet18-f37072fd.pth&quot; to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
 
   0%|          | 0.00/44.7M [00:00&lt;?, ?B/s]
- 18%|#7        | 7.99M/44.7M [00:00&lt;00:00, 62.8MB/s]
- 36%|###5      | 16.0M/44.7M [00:00&lt;00:00, 59.5MB/s]
- 54%|#####4    | 24.1M/44.7M [00:00&lt;00:00, 67.7MB/s]
- 79%|#######8  | 35.1M/44.7M [00:00&lt;00:00, 83.9MB/s]
- 99%|#########8| 44.2M/44.7M [00:00&lt;00:00, 81.7MB/s]
-100%|##########| 44.7M/44.7M [00:00&lt;00:00, 76.8MB/s]
+ 23%|##2       | 10.1M/44.7M [00:00&lt;00:00, 102MB/s]
+ 52%|#####1    | 23.2M/44.7M [00:00&lt;00:00, 123MB/s]
+ 78%|#######8  | 35.0M/44.7M [00:00&lt;00:00, 78.6MB/s]
+100%|##########| 44.7M/44.7M [00:00&lt;00:00, 91.9MB/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 58907cc924..737dbff21d 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -649,7 +649,7 @@ banana (score = 0.00022)
 desk (score = 0.00019)
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  14.973 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  11.413 seconds)</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-tensorflow-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/7f1d3d1b878694c201c614c807cdebc8/from_tensorflow.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_tensorflow.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/sg_execution_times.html b/docs/how_to/compile_models/sg_execution_times.html
index 08a88a1048..083524edde 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -340,7 +340,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:54.740</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:42.455</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 81%" />
@@ -349,43 +349,43 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:14.973</p></td>
+<td><p>01:11.413</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
-<td><p>01:12.301</p></td>
+<td><p>01:09.621</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="from_paddle.html#sphx-glr-how-to-compile-models-from-paddle-py"><span class="std std-ref">Compile PaddlePaddle Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_paddle.py</span></code>)</p></td>
-<td><p>00:48.337</p></td>
+<td><p>00:46.396</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="from_oneflow.html#sphx-glr-how-to-compile-models-from-oneflow-py"><span class="std std-ref">Compile OneFlow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_oneflow.py</span></code>)</p></td>
-<td><p>00:33.114</p></td>
+<td><p>00:32.354</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
-<td><p>00:29.348</p></td>
+<td><p>00:29.166</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
-<td><p>00:27.297</p></td>
+<td><p>00:26.574</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
-<td><p>00:25.617</p></td>
+<td><p>00:25.309</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></td>
-<td><p>00:22.907</p></td>
+<td><p>00:22.370</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="from_keras.html#sphx-glr-how-to-compile-models-from-keras-py"><span class="std std-ref">Compile Keras Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_keras.py</span></code>)</p></td>
-<td><p>00:18.377</p></td>
+<td><p>00:16.812</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="from_onnx.html#sphx-glr-how-to-compile-models-from-onnx-py"><span class="std std-ref">Compile ONNX Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_onnx.py</span></code>)</p></td>
-<td><p>00:02.469</p></td>
+<td><p>00:02.439</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 </tbody>
diff --git a/docs/how_to/deploy_models/deploy_model_on_adreno.html b/docs/how_to/deploy_models/deploy_model_on_adreno.html
index d930119f66..1ff147f849 100644
--- a/docs/how_to/deploy_models/deploy_model_on_adreno.html
+++ b/docs/how_to/deploy_models/deploy_model_on_adreno.html
@@ -920,7 +920,7 @@ Top5 predictions:
 Evaluate inference time cost...
 Execution time summary:
  mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)
- 2541.2335    2540.7646    2543.7993    2539.9691      1.2031
+ 2542.3069    2542.2529    2545.3980    2540.5547      1.2687
 </pre></div>
 </div>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-model-on-adreno-py">
diff --git a/docs/how_to/deploy_models/deploy_model_on_android.html b/docs/how_to/deploy_models/deploy_model_on_android.html
index 78cf81caab..dbb3828bbd 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -662,7 +662,7 @@ to the remote android device.</p>
 Evaluate inference time cost...
 Execution time summary:
  mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)
-  17.0063      17.0883      17.4245      16.2265       0.3316
+  16.3062      15.9608      17.2476      15.7254       0.5920
 </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 7ecff2aca4..0f1b559547 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -454,26 +454,25 @@ be unstable.</p>
 Downloading: &quot;https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth&quot; to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
 
   0%|          | 0.00/170M [00:00&lt;?, ?B/s]
-  4%|3         | 6.30M/170M [00:00&lt;00:03, 55.2MB/s]
-  7%|6         | 11.6M/170M [00:00&lt;00:04, 35.2MB/s]
-  9%|9         | 16.0M/170M [00:00&lt;00:04, 35.8MB/s]
- 12%|#2        | 21.0M/170M [00:00&lt;00:03, 40.9MB/s]
- 15%|#4        | 25.2M/170M [00:00&lt;00:03, 41.0MB/s]
- 22%|##1       | 37.0M/170M [00:00&lt;00:02, 65.6MB/s]
- 28%|##8       | 48.0M/170M [00:00&lt;00:01, 69.0MB/s]
- 33%|###3      | 56.7M/170M [00:01&lt;00:01, 75.0MB/s]
- 38%|###7      | 64.1M/170M [00:01&lt;00:01, 74.8MB/s]
- 45%|####5     | 76.6M/170M [00:01&lt;00:01, 90.6MB/s]
- 51%|#####     | 86.6M/170M [00:01&lt;00:00, 94.5MB/s]
- 56%|#####6    | 95.8M/170M [00:01&lt;00:00, 93.4MB/s]
- 62%|######1   | 105M/170M [00:01&lt;00:00, 70.6MB/s]
- 66%|######6   | 112M/170M [00:01&lt;00:01, 51.8MB/s]
- 75%|#######5  | 128M/170M [00:02&lt;00:00, 68.6MB/s]
- 80%|########  | 136M/170M [00:02&lt;00:00, 65.2MB/s]
- 87%|########6 | 147M/170M [00:02&lt;00:00, 76.5MB/s]
- 92%|#########1| 156M/170M [00:02&lt;00:00, 66.0MB/s]
- 98%|#########8| 167M/170M [00:02&lt;00:00, 77.1MB/s]
-100%|##########| 170M/170M [00:02&lt;00:00, 68.0MB/s]
+  6%|5         | 10.1M/170M [00:00&lt;00:02, 60.6MB/s]
+ 13%|#3        | 22.9M/170M [00:00&lt;00:01, 93.9MB/s]
+ 19%|#9        | 32.8M/170M [00:00&lt;00:01, 78.2MB/s]
+ 24%|##4       | 41.0M/170M [00:00&lt;00:01, 79.7MB/s]
+ 33%|###2      | 55.7M/170M [00:00&lt;00:01, 102MB/s]
+ 39%|###8      | 66.2M/170M [00:00&lt;00:01, 83.1MB/s]
+ 44%|####4     | 75.2M/170M [00:00&lt;00:01, 85.9MB/s]
+ 52%|#####1    | 88.0M/170M [00:01&lt;00:00, 86.6MB/s]
+ 57%|#####6    | 96.7M/170M [00:01&lt;00:00, 80.4MB/s]
+ 62%|######1   | 105M/170M [00:01&lt;00:01, 64.9MB/s]
+ 66%|######6   | 112M/170M [00:01&lt;00:00, 68.5MB/s]
+ 72%|#######1  | 122M/170M [00:01&lt;00:00, 76.1MB/s]
+ 76%|#######6  | 130M/170M [00:01&lt;00:00, 68.1MB/s]
+ 81%|########  | 137M/170M [00:01&lt;00:00, 55.9MB/s]
+ 85%|########4 | 144M/170M [00:02&lt;00:00, 59.9MB/s]
+ 88%|########8 | 150M/170M [00:02&lt;00:00, 58.5MB/s]
+ 93%|#########3| 158M/170M [00:02&lt;00:00, 64.6MB/s]
+ 97%|#########7| 165M/170M [00:02&lt;00:00, 55.3MB/s]
+100%|##########| 170M/170M [00:02&lt;00:00, 70.6MB/s]
 /venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
   for i in range(dim)
 /venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the &#39;trunc&#39; function NOT &#39;floor&#39;). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode=&#39;trunc&#39;), or for actual floor division, use torch.div(a, b, rounding_mode=& [...]
@@ -571,7 +570,7 @@ 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  23.678 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  15.612 seconds)</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-object-detection-pytorch-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/7795da4b258c8feff986668b95ef57ad/deploy_object_detection_pytorch.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_object_detection_pytorch.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_prequantized.html b/docs/how_to/deploy_models/deploy_prequantized.html
index 411a230909..273c0e6694 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -498,9 +498,8 @@ training. Other models require a full post training calibration.</p>
 Downloading: &quot;https://download.pytorch.org/models/mobilenet_v2-b0353104.pth&quot; to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
 
   0%|          | 0.00/13.6M [00:00&lt;?, ?B/s]
- 47%|####6     | 6.30M/13.6M [00:00&lt;00:00, 56.6MB/s]
- 86%|########6 | 11.7M/13.6M [00:00&lt;00:00, 54.1MB/s]
-100%|##########| 13.6M/13.6M [00:00&lt;00:00, 55.4MB/s]
+ 59%|#####8    | 7.99M/13.6M [00:00&lt;00:00, 46.8MB/s]
+100%|##########| 13.6M/13.6M [00:00&lt;00:00, 68.7MB/s]
 </pre></div>
 </div>
 </div>
@@ -591,7 +590,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
  mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)
-  90.9066      90.8621      96.1144      90.2798       0.5811
+  90.1449      90.0781      92.3321      89.9773       0.2632
 </pre></div>
 </div>
 <div class="admonition note">
@@ -630,7 +629,7 @@ This includes support for the VNNI 8 bit dot product instruction (CascadeLake or
 <div class="section" id="deploy-a-quantized-tflite-model">
 <h2>Deploy a quantized TFLite Model<a class="headerlink" href="#deploy-a-quantized-tflite-model" title="Permalink to this headline">¶</a></h2>
 <p>TODO</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  8.878 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  5.543 seconds)</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/fb8217c13f4351224c6cf3aacf1a87fc/deploy_prequantized.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_prequantized.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_prequantized_tflite.html b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
index a512959953..54dbb6dc53 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -583,7 +583,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
  mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)
-  121.3369     121.3223     127.6271     120.3300      0.7701
+  120.0660     119.9553     124.2132     119.3955      0.5039
 </pre></div>
 </div>
 <div class="admonition note">
@@ -611,7 +611,7 @@ 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  23.611 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes  21.747 seconds)</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-tflite-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/56691c7a27d45da61d112276334640d3/deploy_prequantized_tflite.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_prequantized_tflite.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_quantized.html b/docs/how_to/deploy_models/deploy_quantized.html
index e88a5d6c64..a06b43070f 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -521,7 +521,7 @@ 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  30.417 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  26.011 seconds)</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-quantized-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/7810ecf51bfc05f7d5e8a400ac3e815d/deploy_quantized.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_quantized.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
index 6a0c86bb3e..ab62c6a6fb 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -463,24 +463,23 @@ 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&lt;?, ?KB/s]
-  4%|4         | 5735/132723 [00:00&lt;00:02, 57119.22KB/s]
- 10%|#         | 13334/132723 [00:00&lt;00:01, 68196.41KB/s]
- 16%|#5        | 20661/132723 [00:00&lt;00:01, 70503.38KB/s]
- 22%|##1       | 28604/132723 [00:00&lt;00:01, 74022.65KB/s]
- 27%|##7       | 36426/132723 [00:00&lt;00:01, 75532.90KB/s]
- 33%|###3      | 44292/132723 [00:00&lt;00:01, 76593.27KB/s]
- 39%|###9      | 52116/132723 [00:00&lt;00:01, 77125.15KB/s]
- 45%|####5     | 59829/132723 [00:00&lt;00:00, 76953.52KB/s]
- 51%|#####     | 67525/132723 [00:00&lt;00:00, 76673.45KB/s]
- 57%|#####6    | 75193/132723 [00:01&lt;00:00, 76439.33KB/s]
- 62%|######2   | 82838/132723 [00:01&lt;00:00, 76296.43KB/s]
- 68%|######8   | 90468/132723 [00:01&lt;00:00, 76063.71KB/s]
- 74%|#######3  | 98076/132723 [00:01&lt;00:00, 76065.03KB/s]
- 80%|#######9  | 105683/132723 [00:01&lt;00:00, 75780.31KB/s]
- 85%|########5 | 113262/132723 [00:01&lt;00:00, 75679.69KB/s]
- 91%|#########1| 120870/132723 [00:01&lt;00:00, 75798.40KB/s]
- 97%|#########6| 128450/132723 [00:01&lt;00:00, 75732.44KB/s]
-100%|##########| 132723/132723 [00:01&lt;00:00, 75299.00KB/s]
+  4%|4         | 5600/132723 [00:00&lt;00:02, 55993.78KB/s]
+ 10%|9         | 13223/132723 [00:00&lt;00:01, 67889.32KB/s]
+ 16%|#5        | 21134/132723 [00:00&lt;00:01, 73011.08KB/s]
+ 22%|##1       | 29081/132723 [00:00&lt;00:01, 75554.60KB/s]
+ 28%|##7       | 37066/132723 [00:00&lt;00:01, 77102.04KB/s]
+ 34%|###3      | 45115/132723 [00:00&lt;00:01, 78252.43KB/s]
+ 40%|####      | 53116/132723 [00:00&lt;00:01, 78823.45KB/s]
+ 46%|####6     | 61104/132723 [00:00&lt;00:00, 79157.94KB/s]
+ 52%|#####2    | 69172/132723 [00:00&lt;00:00, 79626.51KB/s]
+ 58%|#####8    | 77257/132723 [00:01&lt;00:00, 80000.50KB/s]
+ 64%|######4   | 85258/132723 [00:01&lt;00:00, 79972.62KB/s]
+ 70%|#######   | 93267/132723 [00:01&lt;00:00, 80005.91KB/s]
+ 76%|#######6  | 101310/132723 [00:01&lt;00:00, 80132.81KB/s]
+ 82%|########2 | 109347/132723 [00:01&lt;00:00, 80202.26KB/s]
+ 88%|########8 | 117404/132723 [00:01&lt;00:00, 80303.48KB/s]
+ 95%|#########4| 125435/132723 [00:01&lt;00:00, 80285.59KB/s]
+100%|##########| 132723/132723 [00:01&lt;00:00, 78489.29KB/s]
 </pre></div>
 </div>
 <p>Create TVM runtime and do inference
@@ -519,7 +518,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
 <span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
 </pre></div>
 </div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  11.812 seconds)</p>
+<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  4.930 seconds)</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-ssd-gluoncv-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/cccb17d28e5e8b2e94ea8cd5ec59f6ed/deploy_ssd_gluoncv.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_ssd_gluoncv.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/sg_execution_times.html b/docs/how_to/deploy_models/sg_execution_times.html
index fb4d2fa2f0..ae5ce0180d 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -340,7 +340,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>13:57.688</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>13:29.805</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 86%" />
@@ -349,39 +349,39 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>03:23.678</p></td>
+<td><p>03:15.612</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>03:11.812</p></td>
+<td><p>03:04.930</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized_tflite.html#sphx-glr-how-to-deploy-models-deploy-prequantized-tflite-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite)</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized_tflite.py</span></code>)</p></td>
-<td><p>02:23.611</p></td>
+<td><p>02:21.747</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="deploy_quantized.html#sphx-glr-how-to-deploy-models-deploy-quantized-py"><span class="std std-ref">Deploy a Quantized Model on Cuda</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_quantized.py</span></code>)</p></td>
-<td><p>01:30.417</p></td>
+<td><p>01:26.011</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized.html#sphx-glr-how-to-deploy-models-deploy-prequantized-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized.py</span></code>)</p></td>
-<td><p>01:08.878</p></td>
+<td><p>01:05.543</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_adreno.html#sphx-glr-how-to-deploy-models-deploy-model-on-adreno-py"><span class="std std-ref">Deploy the Pretrained Model on Adreno</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_adreno.py</span></code>)</p></td>
-<td><p>00:52.079</p></td>
+<td><p>00:51.212</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:36.392</p></td>
+<td><p>00:35.522</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_nano.html#sphx-glr-how-to-deploy-models-deploy-model-on-nano-py"><span class="std std-ref">Deploy the Pretrained Model on Jetson Nano</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_nano.py</span></code>)</p></td>
-<td><p>00:25.582</p></td>
+<td><p>00:24.829</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:25.231</p></td>
+<td><p>00:24.394</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index d09607a234..9008a66145 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -622,7 +622,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
 <span class="n">module</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">params</span></a> <span class="o">=</span> <span class="n">get_mobilenet</span><span class="p">()</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip59ffb2db-5533-40ad-899b-c7b06d7441b0 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.zip8393d624-278c-4db7-9a96-9cd1da431001 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 44c700149b..b512b20219 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -340,7 +340,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:48.786</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:46.995</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 84%" />
@@ -349,19 +349,19 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:45.229</p></td>
+<td><p>00:43.551</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="use_pass_instrument.html#sphx-glr-how-to-extend-tvm-use-pass-instrument-py"><span class="std std-ref">How to Use TVM Pass Instrument</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_instrument.py</span></code>)</p></td>
-<td><p>00:02.492</p></td>
+<td><p>00:02.410</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="use_pass_infra.html#sphx-glr-how-to-extend-tvm-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></td>
-<td><p>00:01.058</p></td>
+<td><p>00:01.027</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
-<td><p>00:00.008</p></td>
+<td><p>00:00.007</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 </tbody>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 53f8dde863..020da50f1c 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -526,10 +526,10 @@ profile the execution time of each passes.</p>
 </pre></div>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 7301us [7301us] (46.40%; 46.40%)
-FoldScaleAxis: 8434us [7us] (53.60%; 53.60%)
-        FoldConstant: 8427us [1744us] (53.56%; 99.91%)
-                InferType: 6684us [6684us] (42.48%; 79.31%)
+InferType: 7217us [7217us] (46.46%; 46.46%)
+FoldScaleAxis: 8316us [7us] (53.54%; 53.54%)
+        FoldConstant: 8309us [1694us] (53.49%; 99.92%)
+                InferType: 6616us [6616us] (42.59%; 79.62%)
 </pre></div>
 </div>
 </div>
@@ -551,10 +551,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
 </pre></div>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6879us [6879us] (44.97%; 44.97%)
-FoldScaleAxis: 8420us [6us] (55.03%; 55.03%)
-        FoldConstant: 8414us [1739us] (55.00%; 99.93%)
-                InferType: 6675us [6675us] (43.63%; 79.33%)
+InferType: 6672us [6672us] (44.96%; 44.96%)
+FoldScaleAxis: 8167us [5us] (55.04%; 55.04%)
+        FoldConstant: 8161us [1681us] (55.00%; 99.93%)
+                InferType: 6480us [6480us] (43.67%; 79.40%)
 </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 78abf4ee3d..3c4b3afb44 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -578,7 +578,7 @@ latency of convolution.</p>
 <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;Convolution: </span><span class="si">%f</span><span class="s2"> ms&quot;</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">*</span> <span cl [...]
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.184448 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 49.154689 ms
 </pre></div>
 </div>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-optimize-operators-opt-conv-cuda-py">
diff --git a/docs/how_to/optimize_operators/opt_conv_tensorcore.html b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
index 30f9f2f4dc..a808a7e328 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -915,7 +915,7 @@ be able to run on our build server</p>
     <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms&quot;</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 13.364944 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 13.375894 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 21c09b4a71..96cda4268b 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -475,8 +475,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
 <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;Baseline: </span><span class="si">%f</span><span class="s2">&quot;</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019091
-Baseline: 3.401195
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018804
+Baseline: 3.333080
 </pre></div>
 </div>
 <p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -535,7 +535,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
 <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;Opt1: </span><span class="si">%f</span><span class="s2">&quot;</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.324664
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.300575
 </pre></div>
 </div>
 <p>Here is the generated IR after blocking.</p>
@@ -601,7 +601,7 @@ vastly.</p>
 <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;Opt2: </span><span class="si">%f</span><span class="s2">&quot;</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.352036
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.337051
 </pre></div>
 </div>
 <p>Here is the generated IR after vectorization.</p>
@@ -661,7 +661,7 @@ the access pattern for A matrix is more cache friendly.</p>
 <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;Opt3: </span><span class="si">%f</span><span class="s2">&quot;</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.115808
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.116211
 </pre></div>
 </div>
 <p>Here is the generated IR after loop permutation.</p>
@@ -743,7 +743,7 @@ flattening.</p>
 <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;Opt4: </span><span class="si">%f</span><span class="s2">&quot;</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.107859
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109564
 </pre></div>
 </div>
 <p>Here is the generated IR after array packing.</p>
@@ -828,7 +828,7 @@ write to C when all the block results are ready.</p>
 <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;Opt5: </span><span class="si">%f</span><span class="s2">&quot;</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.110809
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111722
 </pre></div>
 </div>
 <p>Here is the generated IR after blocking.</p>
@@ -917,7 +917,7 @@ write to C when all the block results are ready.</p>
 <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;Opt6: </span><span class="si">%f</span><span class="s2">&quot;</span> <span class="o">%</span> <span class="n">opt6_time</span><span class="p">)</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.146935
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.146651
 </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 8cb2d681f0..f8ef343620 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -340,7 +340,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:35.389</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.657</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 83%" />
@@ -349,15 +349,15 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:32.796</p></td>
+<td><p>00:32.090</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="opt_conv_tensorcore.html#sphx-glr-how-to-optimize-operators-opt-conv-tensorcore-py"><span class="std std-ref">How to optimize convolution using TensorCores</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_tensorcore.py</span></code>)</p></td>
-<td><p>00:01.527</p></td>
+<td><p>00:01.501</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="opt_conv_cuda.html#sphx-glr-how-to-optimize-operators-opt-conv-cuda-py"><span class="std std-ref">How to optimize convolution on GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_cuda.py</span></code>)</p></td>
-<td><p>00:01.067</p></td>
+<td><p>00:01.066</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 </tbody>
diff --git a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
index ff0ea01362..6dd426aae7 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -340,7 +340,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>09:06.359</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>09:04.667</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 85%" />
@@ -349,27 +349,27 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></td>
-<td><p>05:37.180</p></td>
+<td><p>05:30.463</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="tune_network_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-x86-py"><span class="std std-ref">Auto-scheduling a Neural Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_x86.py</span></code>)</p></td>
-<td><p>01:33.553</p></td>
+<td><p>01:31.322</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="tune_network_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></td>
-<td><p>01:02.636</p></td>
+<td><p>01:01.554</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="tune_sparse_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-sparse-x86-py"><span class="std std-ref">Auto-scheduling Sparse Matrix Multiplication on CPU with Custom Sketch Rule</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_sparse_x86.py</span></code>)</p></td>
-<td><p>00:28.895</p></td>
+<td><p>00:38.278</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></td>
-<td><p>00:12.633</p></td>
+<td><p>00:11.980</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></td>
-<td><p>00:11.461</p></td>
+<td><p>00:11.069</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 </tbody>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html b/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
index 7593b09274..ec8803ba03 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
@@ -504,11 +504,11 @@ cooperative fetching, unrolling and operator fusion.</p>
              bias: Buffer(bias_2: Pointer(float32), float32, [1, 512, 1, 1], []),
              compute: Buffer(compute_2: Pointer(float32), float32, [1, 512, 7, 7], [])}
   buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute} {
-  attr [IterVar(blockIdx.x: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;blockIdx.x&quot;)] &quot;thread_extent&quot; = 28;
+  attr [IterVar(blockIdx.x: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;blockIdx.x&quot;)] &quot;thread_extent&quot; = 8;
   allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
-  allocate(pad_temp.shared: Pointer(shared float32), float32, [72]), storage_scope = shared;
-  allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
-  attr [IterVar(threadIdx.x: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64 {
+  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), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 224 {
     conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope=&quot;local&quot;, align=32)[0] = 0f32
     conv2d_nchw_1[1] = 0f32
     conv2d_nchw_1[2] = 0f32
@@ -524,462 +524,1071 @@ cooperative fetching, unrolling and operator fusion.</p>
     conv2d_nchw_1[12] = 0f32
     conv2d_nchw_1[13] = 0f32
     for (rc.outer.outer: int32, 0, 64) {
-      for (ry.outer.outer: int32, 0, 3) {
-        let cse_var_2: int32 = (rc.outer.outer*72)
-        let cse_var_1: int32 = (ry.outer.outer*3)
-         {
-          attr [IterVar(threadIdx.x_1: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64 {
-            if @tir.likely((threadIdx.x_1 &lt; 18), dtype=bool) {
-              pad_temp.shared_1: Buffer(pad_temp.shared, float32, [72], [], scope=&quot;shared&quot;)[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 &lt;= (ry.outer.outer + floormod(blockIdx.x, 7))) &amp;&amp; ((ry.outer.outer + floormod(blockIdx.x, 7)) &lt; 8)) &amp;&amp; (1 &lt;= floormod((threadIdx.x_1*4), 9))) &amp;&amp; (floormod((threadIdx.x_1*4), 9) &lt; 8)), data_3: Buffer(data_2, float32, [25088], [])[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*4), 9)*49)) + (ry.outer.out [...]
-            }
-            if @tir.likely((threadIdx.x_1 &lt; 18), dtype=bool) {
-              pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 &lt;= (ry.outer.outer + floormod(blockIdx.x, 7))) &amp;&amp; ((ry.outer.outer + floormod(blockIdx.x, 7)) &lt; 8)) &amp;&amp; (1 &lt;= floormod(((threadIdx.x_1*4) + 1), 9))) &amp;&amp; (floormod(((threadIdx.x_1*4) + 1), 9) &lt; 8)), data_3[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 1), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], [...]
-            }
-            if @tir.likely((threadIdx.x_1 &lt; 18), dtype=bool) {
-              pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 &lt;= (ry.outer.outer + floormod(blockIdx.x, 7))) &amp;&amp; ((ry.outer.outer + floormod(blockIdx.x, 7)) &lt; 8)) &amp;&amp; (1 &lt;= floormod(((threadIdx.x_1*4) + 2), 9))) &amp;&amp; (floormod(((threadIdx.x_1*4) + 2), 9) &lt; 8)), data_3[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 2), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], [...]
-            }
-            if @tir.likely((threadIdx.x_1 &lt; 18), dtype=bool) {
-              pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 &lt;= (ry.outer.outer + floormod(blockIdx.x, 7))) &amp;&amp; ((ry.outer.outer + floormod(blockIdx.x, 7)) &lt; 8)) &amp;&amp; (1 &lt;= floormod(((threadIdx.x_1*4) + 3), 9))) &amp;&amp; (floormod(((threadIdx.x_1*4) + 3), 9) &lt; 8)), data_3[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 3), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], [...]
-            }
-          }
-          attr [IterVar(threadIdx.x_2: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope=&quot;shared&quot;)[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 64)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 64), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 128)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 128), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 192)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 256)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 256), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 320)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 320), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 384)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 448)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 448), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 512)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 512), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 576)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 640)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 640), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 704)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 704), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 768)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 147456)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 832)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 832), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 896)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 896), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 960)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 184320)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1024), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1088), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 221184)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1216), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1280), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1408), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1472), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 294912)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1600), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1664), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 331776)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1792), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1856), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 368640)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1984), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2048), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 405504)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2176), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2240), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 442368)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2368), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2432), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 479232)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2560), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2624), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 516096)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2752), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2816), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 552960)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2944), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3008), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*48)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*48)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*48)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*48)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*48)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*48)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*48)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+      let cse_var_1: int32 = (rc.outer.outer*72)
+       {
+        attr [IterVar(threadIdx.x_1: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 224;
+        if @tir.likely((threadIdx.x_1 &lt; 216), dtype=bool) {
+          pad_temp.shared_1: Buffer(pad_temp.shared, float32, [648], [], scope=&quot;shared&quot;)[(threadIdx.x_1*3)] = @tir.if_then_else((((3 &lt;= floormod(threadIdx.x_1, 27)) &amp;&amp; (floormod(threadIdx.x_1, 27) &lt; 24)) &amp;&amp; (0 &lt; floormod(threadIdx.x_1, 3))), data_3: Buffer(data_2, float32, [25088], [])[(((((rc.outer.outer*392) + (floordiv(threadIdx.x_1, 27)*49)) + (floordiv(floormod(threadIdx.x_1, 27), 3)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 8)], 0f32, dtype=float32)
+          pad_temp.shared_1[((threadIdx.x_1*3) + 1)] = @tir.if_then_else(((3 &lt;= floormod(threadIdx.x_1, 27)) &amp;&amp; (floormod(threadIdx.x_1, 27) &lt; 24)), data_3[(((((rc.outer.outer*392) + (floordiv(threadIdx.x_1, 27)*49)) + (floordiv(floormod(threadIdx.x_1, 27), 3)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 7)], 0f32, dtype=float32)
+          pad_temp.shared_1[((threadIdx.x_1*3) + 2)] = @tir.if_then_else((((3 &lt;= floormod(threadIdx.x_1, 27)) &amp;&amp; (floormod(threadIdx.x_1, 27) &lt; 24)) &amp;&amp; (floormod(threadIdx.x_1, 3) &lt; 2)), data_3[(((((rc.outer.outer*392) + (floordiv(threadIdx.x_1, 27)*49)) + (floordiv(floormod(threadIdx.x_1, 27), 3)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 6)], 0f32, dtype=float32)
         }
+        attr [IterVar(threadIdx.x_2: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 224;
+        kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope=&quot;shared&quot;)[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 72)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 224;
+        kernel.shared_1[(threadIdx.x_2 + 224)] = kernel_3[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 224), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 224;
+        kernel.shared_1[(threadIdx.x_2 + 448)] = kernel_3[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 448), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 224;
+        kernel.shared_1[(threadIdx.x_2 + 672)] = kernel_3[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 672), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 224;
+        kernel.shared_1[(threadIdx.x_2 + 896)] = kernel_3[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 896), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 224;
+        kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel_3[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1120), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 224;
+        kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel_3[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1344), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 224;
+        kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel_3[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1568), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 224;
+        kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel_3[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1792), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 224;
+        kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel_3[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 72)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72)) + 129024)]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 224;
+        kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel_3[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2240), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 224;
+        kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel_3[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2464), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 224;
+        kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel_3[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2688), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 224;
+        kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel_3[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2912), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 224;
+        kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel_3[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 3136), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 224;
+        kernel.shared_1[(threadIdx.x_2 + 3360)] = kernel_3[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 3360), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 224;
+        kernel.shared_1[(threadIdx.x_2 + 3584)] = kernel_3[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 3584), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 224;
+        kernel.shared_1[(threadIdx.x_2 + 3808)] = kernel_3[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 3808), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 224;
+        kernel.shared_1[(threadIdx.x_2 + 4032)] = kernel_3[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 72)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72)) + 258048)]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 224;
+        kernel.shared_1[(threadIdx.x_2 + 4256)] = kernel_3[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 4256), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 224;
+        if @tir.likely((threadIdx.x_2 &lt; 128), dtype=bool) {
+          kernel.shared_1[(threadIdx.x_2 + 4480)] = kernel_3[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 4480), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+        }
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*9)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*144)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*144)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*144)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*144)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*144)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*144)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*144)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 1)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 1)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 1)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 1)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 1)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 1)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 1)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 2)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 2)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 2)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 2)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 2)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 2)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 8)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 2)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 3)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 3)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 3)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 12)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 3)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 13)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 3)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 3)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 15)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 3)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 4)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 4)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 12)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 4)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 13)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 4)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 4)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 15)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 4)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 16)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 4)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 5)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 12)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 5)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 13)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 5)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 5)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 15)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 5)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 16)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 5)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 17)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 5)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 6)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 6)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 6)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 21)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 6)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 22)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 6)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 23)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 6)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 24)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 6)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 7)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 7)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 21)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 7)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 22)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 7)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 23)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 7)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 24)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 7)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 25)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 7)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 8)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 21)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 8)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 22)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 8)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 23)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 8)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 24)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 8)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 25)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 8)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 26)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 8)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 9)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 9)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 9)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 84)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 9)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 85)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 9)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 86)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 9)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 87)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 9)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 10)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 10)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 84)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 10)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 85)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 10)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 86)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 10)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 87)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 10)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 88)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 10)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 11)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 84)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 11)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 85)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 11)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 86)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 11)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 87)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 11)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 88)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 11)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 89)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 11)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 12)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 12)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 12)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 93)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 12)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 94)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 12)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 95)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 12)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 96)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 12)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 13)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 13)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 93)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 13)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 94)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 13)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 95)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 13)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 96)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 13)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 97)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 13)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 14)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 93)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 14)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 94)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 14)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 95)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 14)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 96)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 14)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 97)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 14)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 14)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 15)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 15)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 15)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 15)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 15)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 15)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 105)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 15)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 16)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 16)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 16)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 16)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 16)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 105)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 16)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 106)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 16)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 17)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 17)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 17)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 17)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 105)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 17)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 106)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 17)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 107)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 17)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 18)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 18)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 18)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 165)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 18)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 166)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 18)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 167)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 18)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 168)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 18)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 19)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 19)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 165)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 19)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 166)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 19)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 167)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 19)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 168)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 19)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 169)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 19)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 20)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 165)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 20)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 166)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 20)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 167)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 20)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 168)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 20)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 169)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 20)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 170)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 20)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 21)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 21)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 21)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 174)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 21)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 175)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 21)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 176)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 21)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 177)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 21)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 22)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 22)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 174)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 22)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 175)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 22)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 176)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 22)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 177)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 22)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 178)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 22)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 23)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 174)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 23)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 175)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 23)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 176)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 23)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 177)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 23)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 178)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 23)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 179)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 23)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 24)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 24)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 24)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 183)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 24)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 184)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 24)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 185)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 24)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 186)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 24)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 25)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 25)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 183)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 25)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 184)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 25)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 185)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 25)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 186)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 25)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 187)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 25)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 26)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 183)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 26)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 184)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 26)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 185)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 26)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 186)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 26)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 187)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 26)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 188)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 26)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 27)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 27)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 27)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 27)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 27)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 27)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 27)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 28)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 28)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 28)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 28)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 28)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 28)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 28)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 29)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 29)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 29)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 29)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 29)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 29)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 29)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 30)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 30)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 30)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 30)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 30)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 30)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 30)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 31)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 31)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 31)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 31)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 31)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 31)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 31)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 32)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 32)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 32)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 32)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 32)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 32)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 260)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 32)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 33)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 33)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 33)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 264)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 33)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 265)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 33)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 266)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 33)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 267)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 33)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 34)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 34)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 264)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 34)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 265)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 34)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 266)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 34)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 267)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 34)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 268)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 34)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 35)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 264)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 35)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 265)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 35)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 266)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 35)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 267)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 35)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 268)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 35)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 269)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 35)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 72)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 72)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 72)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 72)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 72)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 72)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 72)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 73)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 73)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 73)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 73)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 73)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 73)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 73)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 74)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 74)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 74)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 74)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 74)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 74)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 8)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 74)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 75)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 75)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 75)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 12)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 75)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 13)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 75)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 75)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 15)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 75)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 76)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 76)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 12)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 76)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 13)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 76)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 76)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 15)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 76)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 16)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 76)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 77)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 12)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 77)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 13)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 77)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 77)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 15)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 77)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 16)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 77)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 17)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 77)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 78)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 78)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 78)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 21)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 78)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 22)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 78)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 23)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 78)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 24)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 78)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 79)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 79)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 21)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 79)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 22)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 79)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 23)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 79)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 24)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 79)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 25)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 79)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 80)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 21)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 80)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 22)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 80)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 23)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 80)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 24)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 80)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 25)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 80)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 26)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 80)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 81)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 81)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 81)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 84)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 81)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 85)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 81)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 86)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 81)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 87)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 81)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 82)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 82)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 84)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 82)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 85)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 82)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 86)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 82)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 87)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 82)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 88)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 82)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 83)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 84)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 83)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 85)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 83)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 86)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 83)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 87)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 83)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 88)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 83)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 89)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 83)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 84)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 84)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 84)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 93)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 84)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 94)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 84)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 95)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 84)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 96)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 84)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 85)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 85)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 93)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 85)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 94)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 85)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 95)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 85)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 96)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 85)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 97)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 85)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 86)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 93)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 86)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 94)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 86)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 95)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 86)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 96)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 86)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 97)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 86)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 86)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 87)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 87)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 87)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 87)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 87)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 87)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 105)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 87)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 88)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 88)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 88)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 88)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 88)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 105)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 88)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 106)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 88)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 89)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 89)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 89)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 89)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 105)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 89)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 106)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 89)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 107)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 89)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 90)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 90)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 90)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 165)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 90)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 166)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 90)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 167)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 90)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 168)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 90)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 91)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 91)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 165)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 91)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 166)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 91)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 167)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 91)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 168)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 91)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 169)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 91)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 92)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 165)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 92)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 166)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 92)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 167)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 92)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 168)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 92)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 169)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 92)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 170)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 92)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 93)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 93)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 93)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 174)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 93)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 175)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 93)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 176)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 93)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 177)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 93)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 94)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 94)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 174)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 94)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 175)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 94)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 176)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 94)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 177)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 94)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 178)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 94)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 95)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 174)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 95)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 175)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 95)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 176)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 95)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 177)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 95)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 178)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 95)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 179)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 95)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 96)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 96)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 96)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 183)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 96)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 184)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 96)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 185)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 96)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 186)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 96)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 97)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 97)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 183)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 97)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 184)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 97)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 185)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 97)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 186)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 97)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 187)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 97)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 98)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 183)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 98)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 184)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 98)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 185)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 98)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 186)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 98)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 187)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 98)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 188)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 98)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 99)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 99)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 99)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 99)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 99)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 99)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 99)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 100)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 100)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 100)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 100)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 100)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 100)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 100)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 101)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 101)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 101)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 101)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 101)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 101)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 101)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 102)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 102)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 102)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 102)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 102)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 102)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 102)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 103)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 103)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 103)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 103)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 103)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 103)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 103)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 104)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 104)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 104)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 104)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 104)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 104)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 260)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 104)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 105)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 105)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 105)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 264)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 105)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 265)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 105)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 266)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 105)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 267)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 105)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 106)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 106)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 264)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 106)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 265)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 106)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 266)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 106)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 267)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 106)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 268)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 106)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 107)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 264)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 107)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 265)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 107)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 266)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 107)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 267)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 107)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 268)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 107)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 269)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 107)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 324)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 36)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 36)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 36)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 327)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 36)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 328)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 36)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 329)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 36)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 330)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 36)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 37)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 37)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 327)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 37)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 328)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 37)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 329)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 37)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 330)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 37)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 331)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 37)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 38)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 327)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 38)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 328)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 38)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 329)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 38)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 330)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 38)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 331)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 38)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 332)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 38)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 39)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 39)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 39)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 336)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 39)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 337)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 39)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 338)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 39)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 339)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 39)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 40)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 40)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 336)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 40)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 337)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 40)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 338)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 40)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 339)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 40)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 340)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 40)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 41)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 336)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 41)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 337)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 41)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 338)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 41)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 339)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 41)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 340)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 41)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 341)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 41)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 42)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 42)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 42)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 42)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 42)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 42)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 42)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 43)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 43)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 43)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 43)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 43)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 43)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 43)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 44)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 44)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 44)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 44)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 44)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 44)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 350)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 44)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 405)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 45)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 406)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 45)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 45)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 408)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 45)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 409)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 45)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 410)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 45)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 411)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 45)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 406)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 46)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 46)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 408)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 46)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 409)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 46)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 410)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 46)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 411)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 46)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 412)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 46)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 47)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 408)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 47)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 409)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 47)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 410)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 47)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 411)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 47)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 412)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 47)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 413)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 47)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 414)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 48)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 48)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 48)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 417)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 48)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 418)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 48)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 419)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 48)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 420)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 48)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 49)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 49)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 417)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 49)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 418)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 49)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 419)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 49)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 420)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 49)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 421)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 49)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 50)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 417)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 50)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 418)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 50)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 419)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 50)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 420)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 50)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 421)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 50)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 422)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 50)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 51)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 51)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 51)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 426)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 51)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 427)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 51)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 428)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 51)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 429)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 51)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 52)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 52)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 426)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 52)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 427)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 52)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 428)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 52)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 429)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 52)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 430)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 52)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 53)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 426)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 53)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 427)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 53)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 428)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 53)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 429)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 53)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 430)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 53)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 431)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 53)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 486)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 54)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 487)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 54)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 54)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 489)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 54)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 54)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 491)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 54)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 492)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 54)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 487)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 55)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 55)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 489)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 55)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 55)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 491)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 55)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 492)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 55)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 493)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 55)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 56)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 489)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 56)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 56)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 491)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 56)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 492)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 56)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 493)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 56)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 494)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 56)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 495)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 57)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 57)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 57)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 498)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 57)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 499)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 57)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 500)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 57)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 501)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 57)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 58)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 58)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 498)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 58)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 499)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 58)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 500)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 58)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 501)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 58)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 502)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 58)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 59)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 498)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 59)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 499)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 59)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 500)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 59)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 501)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 59)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 502)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 59)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 503)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 59)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 60)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 60)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 60)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 507)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 60)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 508)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 60)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 509)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 60)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 510)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 60)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 61)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 61)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 507)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 61)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 508)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 61)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 509)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 61)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 510)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 61)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 511)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 61)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 62)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 507)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 62)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 508)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 62)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 509)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 62)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 510)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 62)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 511)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 62)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 512)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 62)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 63)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 63)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 63)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 570)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 63)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 571)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 63)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 572)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 63)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 573)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 63)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 64)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 64)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 570)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 64)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 571)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 64)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 572)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 64)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 573)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 64)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 574)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 64)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 65)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 570)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 65)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 571)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 65)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 572)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 65)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 573)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 65)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 574)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 65)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 575)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 65)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 66)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 66)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 66)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 579)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 66)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 580)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 66)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 581)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 66)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 582)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 66)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 67)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 67)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 579)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 67)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 580)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 67)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 581)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 67)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 582)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 67)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 583)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 67)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 68)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 579)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 68)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 580)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 68)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 581)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 68)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 582)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 68)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 583)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 68)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 584)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 68)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 69)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 69)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 69)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 69)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 589)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 69)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 590)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 69)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 591)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 69)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 70)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 70)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 70)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 589)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 70)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 590)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 70)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 591)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 70)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 592)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 70)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 71)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 71)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 589)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 71)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 590)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 71)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 591)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 71)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 592)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 71)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 593)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 71)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 324)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 108)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 108)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 108)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 327)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 108)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 328)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 108)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 329)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 108)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 330)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 108)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 109)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 109)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 327)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 109)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 328)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 109)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 329)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 109)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 330)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 109)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 331)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 109)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 110)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 327)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 110)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 328)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 110)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 329)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 110)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 330)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 110)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 331)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 110)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 332)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 110)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 111)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 111)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 111)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 336)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 111)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 337)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 111)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 338)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 111)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 339)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 111)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 112)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 112)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 336)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 112)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 337)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 112)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 338)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 112)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 339)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 112)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 340)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 112)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 113)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 336)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 113)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 337)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 113)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 338)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 113)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 339)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 113)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 340)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 113)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 341)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 113)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 114)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 114)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 114)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 114)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 114)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 114)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 114)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 115)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 115)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 115)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 115)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 115)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 115)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 115)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 116)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 116)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 116)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 116)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 116)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 116)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 350)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 116)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 405)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 117)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 406)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 117)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 117)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 408)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 117)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 409)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 117)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 410)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 117)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 411)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 117)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 406)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 118)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 118)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 408)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 118)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 409)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 118)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 410)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 118)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 411)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 118)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 412)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 118)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 119)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 408)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 119)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 409)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 119)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 410)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 119)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 411)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 119)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 412)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 119)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 413)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 119)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 414)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 120)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 120)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 120)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 417)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 120)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 418)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 120)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 419)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 120)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 420)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 120)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 121)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 121)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 417)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 121)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 418)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 121)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 419)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 121)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 420)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 121)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 421)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 121)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 122)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 417)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 122)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 418)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 122)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 419)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 122)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 420)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 122)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 421)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 122)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 422)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 122)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 123)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 123)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 123)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 426)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 123)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 427)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 123)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 428)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 123)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 429)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 123)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 124)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 124)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 426)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 124)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 427)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 124)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 428)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 124)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 429)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 124)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 430)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 124)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 125)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 426)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 125)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 427)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 125)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 428)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 125)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 429)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 125)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 430)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 125)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 431)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 125)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 486)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 126)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 487)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 126)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 126)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 489)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 126)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 126)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 491)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 126)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 492)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 126)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 487)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 127)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 127)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 489)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 127)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 127)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 491)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 127)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 492)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 127)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 493)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 127)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 128)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 489)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 128)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 128)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 491)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 128)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 492)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 128)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 493)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 128)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 494)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 128)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 495)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 129)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 129)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 129)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 498)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 129)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 499)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 129)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 500)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 129)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 501)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 129)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 130)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 130)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 498)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 130)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 499)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 130)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 500)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 130)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 501)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 130)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 502)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 130)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 131)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 498)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 131)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 499)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 131)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 500)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 131)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 501)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 131)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 502)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 131)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 503)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 131)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 132)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 132)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 132)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 507)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 132)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 508)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 132)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 509)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 132)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 510)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 132)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 133)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 133)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 507)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 133)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 508)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 133)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 509)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 133)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 510)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 133)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 511)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 133)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 134)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 507)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 134)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 508)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 134)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 509)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 134)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 510)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 134)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 511)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 134)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 512)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 134)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 135)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 135)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 135)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 570)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 135)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 571)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 135)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 572)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 135)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 573)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 135)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 136)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 136)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 570)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 136)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 571)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 136)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 572)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 136)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 573)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 136)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 574)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 136)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 137)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 570)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 137)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 571)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 137)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 572)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 137)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 573)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 137)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 574)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 137)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 575)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 137)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 138)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 138)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 138)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 579)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 138)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 580)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 138)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 581)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 138)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 582)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 138)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 139)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 139)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 579)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 139)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 580)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 139)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 581)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 139)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 582)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 139)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 583)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 139)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 140)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 579)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 140)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 580)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 140)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 581)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 140)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 582)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 140)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 583)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 140)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 584)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 140)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 141)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 141)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 141)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 141)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 589)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 141)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 590)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 141)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 591)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 141)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 142)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 142)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 142)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 589)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 142)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 590)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 142)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 591)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 142)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 592)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 142)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 143)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 143)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 589)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 143)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 590)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 143)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 591)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 143)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 592)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 143)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 593)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 143)]))
       }
     }
     for (i1.inner: int32, 0, 2) {
       for (i3.inner: int32, 0, 7) {
-        compute_3: Buffer(compute_2, float32, [25088], [])[(((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias_3: Buffer(bias_2, float32, [512], [])[(((floordiv(blockIdx.x, 7)*128) + (threadIdx.x*2)) + i1.inner)]), 0f32)
+        compute_3: Buffer(compute_2, float32, [25088], [])[(((((blockIdx.x*3136) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias_3: Buffer(bias_2, float32, [512], [])[(((blockIdx.x*64) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
       }
     }
   }
@@ -1017,7 +1626,7 @@ cooperative fetching, unrolling and operator fusion.</p>
 <span class="p">)</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.366 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.275 ms
 </pre></div>
 </div>
 </div>
@@ -1048,31 +1657,31 @@ conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_
 conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
 conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
 conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
+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=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_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
 conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
-conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
-conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
+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=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=1)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
+conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
 conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
-conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=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)
 compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
 compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
+compute_i1_o_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=1)
-compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
 compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
 compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
 compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
@@ -1095,14 +1704,14 @@ 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=64)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=224)
 s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis(&quot;threadIdx.x&quot;))
 pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=4)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=3)
 s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=224)
 s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis(&quot;threadIdx.x&quot;))
-s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, &quot;auto_unroll_max_step&quot;, 512)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, &quot;auto_unroll_max_step&quot;, 1024)
 s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, &quot;unroll_explicit&quot;, True)
 
 CUDA source code:
@@ -1120,10 +1729,10 @@ CUDA source code:
   #define int64_t long long
   #define uint64_t unsigned long long
 #endif
-extern &quot;C&quot; __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+extern &quot;C&quot; __global__ void __launch_bounds__(224) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
   float conv2d_nchw[14];
-  __shared__ float pad_temp_shared[72];
-  __shared__ float kernel_shared[3072];
+  __shared__ float pad_temp_shared[648];
+  __shared__ float kernel_shared[4608];
   conv2d_nchw[0] = 0.000000e+00f;
   conv2d_nchw[1] = 0.000000e+00f;
   conv2d_nchw[2] = 0.000000e+00f;
@@ -1139,410 +1748,1048 @@ extern &quot;C&quot; __global__ void __launch_bounds__(64) default_function_kern
   conv2d_nchw[12] = 0.000000e+00f;
   conv2d_nchw[13] = 0.000000e+00f;
   for (int rc_outer_outer = 0; rc_outer_outer &lt; 64; ++rc_outer_outer) {
-    for (int ry_outer_outer = 0; ry_outer_outer &lt; 3; ++ry_outer_outer) {
-      __syncthreads();
-      if (((int)threadIdx.x) &lt; 18) {
-        pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 &lt;= (ry_outer_outer + (((int)blockIdx.x) % 7))) &amp;&amp; ((ry_outer_outer + (((int)blockIdx.x) % 7)) &lt; 8)) &amp;&amp; (1 &lt;= ((((int)threadIdx.x) * 4) % 9))) &amp;&amp; (((((int)threadIdx.x) * 4) % 9) &lt; 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
-      }
-      if (((int)threadIdx.x) &lt; 18) {
-        pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 &lt;= (ry_outer_outer + (((int)blockIdx.x) % 7))) &amp;&amp; ((ry_outer_outer + (((int)blockIdx.x) % 7)) &lt; 8)) &amp;&amp; (1 &lt;= (((((int)threadIdx.x) * 4) + 1) % 9))) &amp;&amp; ((((((int)threadIdx.x) * 4) + 1) % 9) &lt; 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
-      }
-      if (((int)threadIdx.x) &lt; 18) {
-        pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 &lt;= (ry_outer_outer + (((int)blockIdx.x) % 7))) &amp;&amp; ((ry_outer_outer + (((int)blockIdx.x) % 7)) &lt; 8)) &amp;&amp; (1 &lt;= (((((int)threadIdx.x) * 4) + 2) % 9))) &amp;&amp; ((((((int)threadIdx.x) * 4) + 2) % 9) &lt; 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
-      }
-      if (((int)threadIdx.x) &lt; 18) {
-        pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 &lt;= (ry_outer_outer + (((int)blockIdx.x) % 7))) &amp;&amp; ((ry_outer_outer + (((int)blockIdx.x) % 7)) &lt; 8)) &amp;&amp; (1 &lt;= (((((int)threadIdx.x) * 4) + 3) % 9))) &amp;&amp; ((((((int)threadIdx.x) * 4) + 3) % 9) &lt; 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
-      }
-      kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
-      kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
-      kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
-      kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
-      kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
-      kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
-      kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
-      kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
-      kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
-      kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
-      kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
-      kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
-      kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
-      kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
-      kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
-      kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      __syncthreads();
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 48)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 48)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 48)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 48)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 48)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 48)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 48)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+    __syncthreads();
+    if (((int)threadIdx.x) &lt; 216) {
+      pad_temp_shared[(((int)threadIdx.x) * 3)] = ((((3 &lt;= (((int)threadIdx.x) % 27)) &amp;&amp; ((((int)threadIdx.x) % 27) &lt; 24)) &amp;&amp; (0 &lt; (((int)threadIdx.x) % 3))) ? data[(((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 27) * 49)) + (((((int)threadIdx.x) % 27) / 3) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 8)] : 0.000000e+00f);
+      pad_temp_shared[((((int)threadIdx.x) * 3) + 1)] = (((3 &lt;= (((int)threadIdx.x) % 27)) &amp;&amp; ((((int)threadIdx.x) % 27) &lt; 24)) ? data[(((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 27) * 49)) + (((((int)threadIdx.x) % 27) / 3) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 7)] : 0.000000e+00f);
+      pad_temp_shared[((((int)threadIdx.x) * 3) + 2)] = ((((3 &lt;= (((int)threadIdx.x) % 27)) &amp;&amp; ((((int)threadIdx.x) % 27) &lt; 24)) &amp;&amp; ((((int)threadIdx.x) % 3) &lt; 2)) ? data[(((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 27) * 49)) + (((((int)threadIdx.x) % 27) / 3) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 6)] : 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) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+    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) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+    kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 672) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+    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) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+    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) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+    kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1344) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+    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) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+    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) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+    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) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+    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) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+    kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2688) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+    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) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+    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) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+    kernel_shared[(((int)threadIdx.x) + 3360)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3360) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+    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) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+    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) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+    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) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+    if (((int)threadIdx.x) &lt; 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) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
     }
+    __syncthreads();
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 9)] * kernel_shared[((((int)threadIdx.x) / 7) * 144)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[((((int)threadIdx.x) / 7) * 144)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[((((int)threadIdx.x) / 7) * 144)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[((((int)threadIdx.x) / 7) * 144)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[((((int)threadIdx.x) / 7) * 144)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[((((int)threadIdx.x) / 7) * 144)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[((((int)threadIdx.x) / 7) * 144)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 1)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 1)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 1)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 1)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 1)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 1)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 1)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 2)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 2)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 2)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 2)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 2)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 2)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 8)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 2)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 3)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 3)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 3)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 3)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 3)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 3)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 3)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 4)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 4)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 4)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 4)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 4)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 4)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 16)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 4)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 5)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 5)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 5)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 5)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 5)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 16)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 5)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 17)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 5)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 6)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 6)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 6)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 6)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 6)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 6)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 24)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 6)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 7)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 7)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 7)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 7)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 7)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 24)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 7)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 25)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 7)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 8)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 8)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 8)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 8)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 24)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 8)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 25)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 8)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 26)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 8)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 9)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 9)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 9)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 9)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 9)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 9)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 9)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 10)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 10)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 10)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 10)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 10)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 10)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 88)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 10)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 11)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 11)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 11)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 11)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 11)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 88)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 11)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 89)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 11)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 12)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 12)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 12)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 93)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 12)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 94)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 12)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 95)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 12)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 96)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 12)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 13)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 13)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 93)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 13)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 94)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 13)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 95)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 13)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 96)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 13)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 97)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 13)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 14)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 93)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 14)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 94)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 14)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 95)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 14)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 96)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 14)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 97)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 14)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 14)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 15)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 15)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 15)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 15)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 15)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 15)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 105)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 15)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 16)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 16)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 16)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 16)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 16)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 105)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 16)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 106)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 16)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 17)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 17)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 17)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 17)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 105)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 17)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 106)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 17)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 107)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 17)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 162)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 18)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 163)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 18)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 18)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 165)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 18)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 166)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 18)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 167)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 18)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 168)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 18)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 163)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 19)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 19)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 165)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 19)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 166)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 19)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 167)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 19)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 168)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 19)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 169)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 19)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 20)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 165)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 20)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 166)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 20)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 167)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 20)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 168)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 20)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 169)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 20)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 170)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 20)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 171)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 21)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 21)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 21)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 174)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 21)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 175)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 21)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 176)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 21)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 177)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 21)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 22)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 22)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 174)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 22)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 175)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 22)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 176)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 22)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 177)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 22)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 178)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 22)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 23)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 174)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 23)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 175)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 23)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 176)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 23)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 177)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 23)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 178)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 23)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 179)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 23)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 24)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 24)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 24)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 183)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 24)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 184)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 24)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 185)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 24)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 186)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 24)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 25)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 25)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 183)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 25)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 184)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 25)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 185)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 25)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 186)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 25)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 187)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 25)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 26)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 183)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 26)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 184)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 26)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 185)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 26)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 186)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 26)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 187)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 26)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 188)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 26)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 243)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 27)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 244)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 27)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 27)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 27)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 27)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 27)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 27)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 244)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 28)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 28)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 28)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 28)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 28)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 28)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 28)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 29)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 29)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 29)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 29)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 29)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 29)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 29)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 30)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 30)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 30)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 30)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 30)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 30)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 30)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 31)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 31)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 31)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 31)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 31)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 31)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 31)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 32)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 32)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 32)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 32)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 32)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 32)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 260)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 32)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 33)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 33)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 33)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 264)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 33)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 265)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 33)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 266)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 33)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 267)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 33)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 34)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 34)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 264)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 34)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 265)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 34)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 266)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 34)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 267)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 34)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 268)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 34)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 35)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 264)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 35)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 265)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 35)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 266)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 35)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 267)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 35)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 268)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 35)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 269)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 35)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 72)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 72)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 72)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 72)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 72)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 72)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 72)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 73)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 73)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 73)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 73)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 73)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 73)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 73)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 74)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 74)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 74)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 74)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 74)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 74)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 8)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 74)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 75)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 75)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 75)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 75)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 75)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 75)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 75)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 76)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 76)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 76)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 76)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 76)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 76)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 16)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 76)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 77)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 77)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 77)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 77)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 77)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 16)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 77)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 17)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 77)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 78)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 78)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 78)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 78)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 78)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 78)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 24)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 78)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 79)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 79)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 79)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 79)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 79)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 24)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 79)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 25)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 79)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 80)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 80)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 80)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 80)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 24)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 80)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 25)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 80)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 26)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 80)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 81)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 81)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 81)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 81)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 81)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 81)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 81)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 82)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 82)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 82)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 82)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 82)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 82)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 88)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 82)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 83)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 83)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 83)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 83)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 83)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 88)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 83)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 89)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 83)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 84)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 84)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 84)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 93)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 84)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 94)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 84)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 95)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 84)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 96)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 84)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 85)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 85)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 93)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 85)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 94)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 85)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 95)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 85)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 96)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 85)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 97)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 85)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 86)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 93)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 86)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 94)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 86)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 95)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 86)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 96)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 86)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 97)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 86)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 86)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 87)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 87)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 87)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 87)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 87)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 87)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 105)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 87)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 88)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 88)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 88)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 88)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 88)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 105)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 88)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 106)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 88)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 89)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 89)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 89)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 89)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 105)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 89)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 106)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 89)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 107)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 89)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 162)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 90)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 163)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 90)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 90)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 165)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 90)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 166)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 90)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 167)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 90)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 168)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 90)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 163)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 91)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 91)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 165)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 91)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 166)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 91)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 167)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 91)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 168)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 91)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 169)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 91)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 92)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 165)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 92)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 166)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 92)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 167)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 92)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 168)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 92)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 169)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 92)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 170)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 92)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 171)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 93)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 93)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 93)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 174)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 93)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 175)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 93)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 176)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 93)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 177)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 93)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 94)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 94)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 174)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 94)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 175)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 94)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 176)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 94)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 177)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 94)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 178)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 94)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 95)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 174)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 95)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 175)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 95)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 176)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 95)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 177)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 95)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 178)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 95)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 179)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 95)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 96)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 96)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 96)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 183)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 96)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 184)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 96)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 185)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 96)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 186)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 96)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 97)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 97)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 183)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 97)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 184)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 97)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 185)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 97)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 186)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 97)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 187)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 97)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 98)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 183)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 98)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 184)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 98)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 185)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 98)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 186)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 98)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 187)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 98)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 188)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 98)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 243)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 99)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 244)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 99)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 99)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 99)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 99)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 99)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 99)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 244)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 100)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 100)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 100)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 100)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 100)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 100)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 100)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 101)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 101)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 101)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 101)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 101)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 101)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 101)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 102)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 102)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 102)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 102)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 102)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 102)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 102)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 103)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 103)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 103)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 103)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 103)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 103)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 103)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 104)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 104)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 104)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 104)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 104)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 104)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 260)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 104)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 105)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 105)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 105)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 264)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 105)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 265)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 105)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 266)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 105)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 267)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 105)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 106)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 106)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 264)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 106)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 265)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 106)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 266)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 106)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 267)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 106)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 268)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 106)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 107)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 264)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 107)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 265)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 107)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 266)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 107)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 267)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 107)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 268)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 107)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 269)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 107)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 324)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 36)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 325)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 36)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 326)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 36)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 327)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 36)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 328)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 36)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 329)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 36)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 330)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 36)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 325)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 37)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 326)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 37)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 327)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 37)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 328)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 37)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 329)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 37)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 330)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 37)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 331)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 37)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 326)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 38)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 327)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 38)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 328)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 38)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 329)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 38)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 330)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 38)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 331)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 38)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 332)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 38)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 333)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 39)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 334)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 39)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 335)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 39)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 336)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 39)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 337)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 39)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 338)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 39)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 339)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 39)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 334)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 40)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 335)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 40)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 336)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 40)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 337)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 40)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 338)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 40)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 339)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 40)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 340)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 40)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 335)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 41)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 336)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 41)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 337)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 41)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 338)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 41)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 339)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 41)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 340)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 41)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 341)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 41)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 342)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 42)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 42)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 42)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 42)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 42)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 42)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 42)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 43)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 43)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 43)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 43)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 43)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 43)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 43)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 44)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 44)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 44)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 44)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 44)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 44)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 350)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 44)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 405)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 45)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 406)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 45)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 407)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 45)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 408)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 45)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 409)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 45)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 410)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 45)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 411)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 45)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 406)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 46)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 407)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 46)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 408)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 46)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 409)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 46)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 410)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 46)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 411)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 46)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 412)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 46)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 407)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 47)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 408)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 47)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 409)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 47)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 410)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 47)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 411)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 47)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 412)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 47)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 413)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 47)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 414)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 48)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 415)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 48)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 416)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 48)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 417)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 48)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 418)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 48)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 419)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 48)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 420)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 48)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 415)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 49)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 416)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 49)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 417)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 49)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 418)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 49)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 419)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 49)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 420)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 49)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 421)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 49)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 416)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 50)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 417)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 50)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 418)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 50)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 419)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 50)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 420)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 50)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 421)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 50)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 422)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 50)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 423)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 51)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 424)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 51)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 425)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 51)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 426)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 51)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 427)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 51)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 428)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 51)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 429)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 51)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 424)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 52)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 425)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 52)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 426)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 52)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 427)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 52)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 428)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 52)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 429)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 52)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 430)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 52)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 425)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 53)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 426)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 53)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 427)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 53)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 428)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 53)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 429)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 53)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 430)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 53)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 431)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 53)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 486)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 54)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 487)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 54)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 488)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 54)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 489)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 54)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 490)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 54)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 491)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 54)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 492)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 54)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 487)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 55)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 488)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 55)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 489)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 55)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 490)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 55)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 491)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 55)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 492)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 55)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 493)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 55)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 488)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 56)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 489)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 56)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 490)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 56)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 491)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 56)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 492)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 56)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 493)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 56)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 494)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 56)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 495)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 57)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 496)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 57)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 497)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 57)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 498)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 57)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 499)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 57)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 500)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 57)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 501)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 57)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 496)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 58)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 497)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 58)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 498)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 58)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 499)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 58)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 500)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 58)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 501)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 58)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 502)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 58)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 497)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 59)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 498)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 59)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 499)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 59)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 500)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 59)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 501)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 59)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 502)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 59)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 503)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 59)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 504)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 60)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 505)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 60)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 60)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 507)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 60)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 508)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 60)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 509)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 60)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 510)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 60)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 505)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 61)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 61)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 507)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 61)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 508)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 61)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 509)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 61)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 510)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 61)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 511)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 61)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 62)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 507)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 62)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 508)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 62)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 509)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 62)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 510)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 62)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 511)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 62)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 512)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 62)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 567)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 63)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 568)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 63)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 569)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 63)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 570)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 63)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 571)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 63)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 572)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 63)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 573)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 63)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 568)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 64)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 569)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 64)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 570)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 64)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 571)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 64)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 572)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 64)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 573)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 64)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 574)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 64)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 569)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 65)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 570)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 65)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 571)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 65)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 572)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 65)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 573)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 65)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 574)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 65)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 575)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 65)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 576)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 66)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 577)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 66)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 578)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 66)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 579)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 66)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 580)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 66)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 581)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 66)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 582)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 66)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 577)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 67)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 578)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 67)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 579)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 67)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 580)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 67)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 581)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 67)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 582)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 67)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 583)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 67)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 578)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 68)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 579)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 68)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 580)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 68)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 581)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 68)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 582)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 68)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 583)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 68)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 584)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 68)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 585)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 69)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 586)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 69)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 69)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 588)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 69)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 589)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 69)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 590)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 69)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 591)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 69)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 586)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 70)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 70)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 588)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 70)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 589)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 70)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 590)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 70)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 591)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 70)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 592)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 70)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 71)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 588)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 71)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 589)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 71)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 590)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 71)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 591)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 71)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 592)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 71)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 593)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 71)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 324)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 108)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 325)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 108)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 326)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 108)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 327)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 108)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 328)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 108)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 329)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 108)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 330)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 108)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 325)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 109)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 326)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 109)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 327)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 109)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 328)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 109)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 329)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 109)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 330)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 109)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 331)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 109)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 326)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 110)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 327)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 110)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 328)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 110)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 329)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 110)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 330)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 110)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 331)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 110)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 332)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 110)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 333)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 111)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 334)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 111)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 335)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 111)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 336)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 111)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 337)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 111)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 338)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 111)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 339)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 111)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 334)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 112)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 335)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 112)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 336)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 112)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 337)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 112)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 338)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 112)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 339)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 112)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 340)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 112)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 335)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 113)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 336)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 113)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 337)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 113)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 338)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 113)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 339)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 113)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 340)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 113)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 341)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 113)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 342)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 114)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 114)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 114)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 114)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 114)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 114)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 114)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 115)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 115)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 115)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 115)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 115)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 115)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 115)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 116)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 116)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 116)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 116)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 116)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 116)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 350)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 116)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 405)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 117)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 406)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 117)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 407)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 117)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 408)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 117)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 409)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 117)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 410)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 117)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 411)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 117)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 406)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 118)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 407)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 118)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 408)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 118)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 409)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 118)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 410)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 118)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 411)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 118)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 412)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 118)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 407)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 119)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 408)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 119)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 409)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 119)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 410)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 119)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 411)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 119)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 412)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 119)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 413)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 119)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 414)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 120)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 415)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 120)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 416)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 120)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 417)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 120)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 418)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 120)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 419)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 120)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 420)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 120)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 415)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 121)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 416)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 121)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 417)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 121)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 418)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 121)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 419)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 121)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 420)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 121)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 421)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 121)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 416)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 122)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 417)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 122)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 418)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 122)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 419)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 122)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 420)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 122)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 421)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 122)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 422)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 122)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 423)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 123)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 424)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 123)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 425)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 123)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 426)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 123)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 427)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 123)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 428)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 123)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 429)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 123)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 424)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 124)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 425)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 124)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 426)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 124)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 427)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 124)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 428)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 124)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 429)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 124)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 430)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 124)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 425)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 125)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 426)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 125)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 427)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 125)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 428)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 125)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 429)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 125)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 430)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 125)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 431)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 125)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 486)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 126)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 487)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 126)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 488)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 126)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 489)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 126)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 490)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 126)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 491)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 126)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 492)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 126)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 487)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 127)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 488)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 127)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 489)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 127)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 490)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 127)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 491)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 127)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 492)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 127)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 493)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 127)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 488)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 128)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 489)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 128)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 490)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 128)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 491)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 128)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 492)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 128)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 493)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 128)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 494)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 128)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 495)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 129)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 496)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 129)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 497)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 129)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 498)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 129)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 499)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 129)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 500)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 129)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 501)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 129)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 496)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 130)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 497)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 130)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 498)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 130)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 499)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 130)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 500)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 130)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 501)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 130)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 502)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 130)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 497)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 131)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 498)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 131)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 499)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 131)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 500)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 131)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 501)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 131)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 502)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 131)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 503)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 131)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 504)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 132)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 505)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 132)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 132)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 507)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 132)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 508)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 132)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 509)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 132)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 510)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 132)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 505)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 133)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 133)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 507)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 133)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 508)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 133)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 509)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 133)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 510)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 133)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 511)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 133)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 134)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 507)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 134)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 508)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 134)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 509)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 134)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 510)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 134)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 511)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 134)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 512)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 134)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 567)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 135)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 568)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 135)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 569)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 135)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 570)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 135)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 571)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 135)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 572)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 135)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 573)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 135)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 568)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 136)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 569)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 136)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 570)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 136)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 571)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 136)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 572)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 136)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 573)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 136)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 574)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 136)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 569)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 137)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 570)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 137)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 571)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 137)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 572)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 137)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 573)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 137)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 574)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 137)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 575)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 137)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 576)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 138)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 577)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 138)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 578)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 138)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 579)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 138)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 580)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 138)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 581)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 138)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 582)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 138)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 577)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 139)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 578)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 139)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 579)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 139)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 580)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 139)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 581)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 139)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 582)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 139)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 583)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 139)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 578)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 140)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 579)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 140)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 580)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 140)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 581)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 140)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 582)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 140)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 583)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 140)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 584)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 140)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 585)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 141)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 586)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 141)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 141)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 588)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 141)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 589)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 141)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 590)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 141)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 591)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 141)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 586)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 142)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 142)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 588)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 142)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 589)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 142)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 590)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 142)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 591)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 142)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 592)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 142)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 143)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 588)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 143)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 589)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 143)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 590)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 143)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 591)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 143)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 592)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 143)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 593)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 143)]));
   }
   for (int i1_inner = 0; i1_inner &lt; 2; ++i1_inner) {
     for (int i3_inner = 0; i3_inner &lt; 7; ++i3_inner) {
-      compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
+      compute[(((((((int)blockIdx.x) * 3136) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[(((((int)blockIdx.x) * 64) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
     }
   }
 }
@@ -1580,7 +2827,7 @@ In the example below we resume the status and do more 5 trials.</p>
 Get devices for measurement successfully!
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes  37.180 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes  30.463 seconds)</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/e3e540f3b477c0c52d8eb73e674e8ffd/tune_conv2d_layer_cuda.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tune_conv2d_layer_cuda.py</span></code></a></p>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
index 26184737cc..3874a63162 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -916,7 +916,7 @@ so we can read the log file and load the best schedules.</p>
 Evaluate inference time cost...
 Execution time summary:
  mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)
-   7.8641       7.8585       7.8794       7.8543       0.0110
+   7.9025       7.9078       7.9138       7.8859       0.0120
 </pre></div>
 </div>
 </div>
@@ -938,7 +938,7 @@ 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  2.636 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  1.554 seconds)</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-network-cuda-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/eafe360d52540634c9eea0fa89e804bd/tune_network_cuda.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tune_network_cuda.py</span></code></a></p>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
index 96f0640c63..11d4add0c4 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -935,7 +935,7 @@ 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)
-  764.2900     764.1682     765.1351     763.5668      0.6460
+  748.4852     748.3161     748.9514     748.1880      0.3338
 </pre></div>
 </div>
 </div>
@@ -957,7 +957,7 @@ to learn how to use the RPC Tracker and RPC Server.
 To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
 with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
 </ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  33.553 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  31.322 seconds)</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-network-x86-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/e416b94ca1090b0897c0f6e0df95b911/tune_network_x86.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tune_network_x86.py</span></code></a></p>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
index 7cd2a26d32..0cdcf8440a 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -633,28 +633,80 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
              placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [128, 512], []),
              compute: Buffer(compute_2: Pointer(float32), float32, [128, 512], [])}
   buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute} {
-  allocate(compute_3: Pointer(global float32), float32, [2048]), storage_scope = global;
-  for (i1.outer: int32, 0, 32) {
-    for (i.outer.inner: int32, 0, 32) {
-      for (i.inner.init: int32, 0, 4) {
-        for (j.init: int32, 0, 16) {
-          compute_4: Buffer(compute_3, float32, [2048], [])[(((i.outer.inner*64) + (i.inner.init*16)) + j.init)] = 0f32
-        }
-      }
-      for (elem_idx: int32, 0, (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(i1.outer + 1)] - placeholder_15[i1.outer])) {
-        for (i.inner: int32, 0, 4) {
-          for (j: int32, 0, 16) {
-            if @tir.likely((elem_idx &lt; (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
-              let cse_var_1: int32 = (((i.outer.inner*64) + (i.inner*16)) + j)
-              compute_4[cse_var_1] = (compute_4[cse_var_1] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + j)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[(((i.outer.inner*1024) + (i.inner*256)) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[i1.outer] + elem_idx)])], 0f32)))
+  for (i0.outer.i1.outer.fused: int32, 0, 16) &quot;parallel&quot; {
+    allocate(compute_3: Pointer(global float32), float32, [4096]), storage_scope = global {
+      for (i.outer.inner: int32, 0, 4) {
+        for (nb_j.inner: int32, 0, 2) {
+          for (i.inner.init: int32, 0, 32) {
+            let cse_var_1: int32 = (((i.outer.inner*1024) + (i.inner.init*32)) + (nb_j.inner*16))
+             {
+              compute_4: Buffer(compute_3, float32, [4096], [])[cse_var_1] = 0f32
+              compute_4[(cse_var_1 + 1)] = 0f32
+              compute_4[(cse_var_1 + 2)] = 0f32
+              compute_4[(cse_var_1 + 3)] = 0f32
+              compute_4[(cse_var_1 + 4)] = 0f32
+              compute_4[(cse_var_1 + 5)] = 0f32
+              compute_4[(cse_var_1 + 6)] = 0f32
+              compute_4[(cse_var_1 + 7)] = 0f32
+              compute_4[(cse_var_1 + 8)] = 0f32
+              compute_4[(cse_var_1 + 9)] = 0f32
+              compute_4[(cse_var_1 + 10)] = 0f32
+              compute_4[(cse_var_1 + 11)] = 0f32
+              compute_4[(cse_var_1 + 12)] = 0f32
+              compute_4[(cse_var_1 + 13)] = 0f32
+              compute_4[(cse_var_1 + 14)] = 0f32
+              compute_4[(cse_var_1 + 15)] = 0f32
+            }
+          }
+          for (elem_idx: int32, 0, let cse_var_2: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_2 + 1)] - placeholder_15[cse_var_2])) {
+            for (i.inner: int32, 0, 32) {
+              let cse_var_21: int32 = (elem_idx*16)
+              let cse_var_20: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
+              let cse_var_19: int32 = ((i.outer.inner*8192) + (i.inner*256))
+              let cse_var_18: int32 = (((i.outer.inner*1024) + (i.inner*32)) + (nb_j.inner*16))
+              let cse_var_17: int32 = (cse_var_18 + 9)
... 4387 lines suppressed ...