[tvm-site] branch asf-site updated: deploying docs (apache/tvm@4f431c87c2b8bb5ea0773c44d92658e506251dda)

[tq...@apache.org]

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 aa09a2939 deploying docs (apache/tvm@4f431c87c2b8bb5ea0773c44d92658e506251dda)
aa09a2939 is described below

commit aa09a2939e33a4a6fa58ebf6c6543b1e29ad5851
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Fri Aug 26 12:20:20 2022 +0000

    deploying docs (apache/tvm@4f431c87c2b8bb5ea0773c44d92658e506251dda)
---
 .../how_to/compile_models/from_darknet.rst.txt     |    5 +
 .../how_to/compile_models/from_mxnet.rst.txt       |    2 +-
 .../how_to/compile_models/from_oneflow.rst.txt     |    2 +-
 .../how_to/compile_models/from_pytorch.rst.txt     |    2 +-
 .../how_to/compile_models/from_tensorflow.rst.txt  |    2 +-
 .../compile_models/sg_execution_times.rst.txt      |   22 +-
 .../deploy_models/deploy_model_on_android.rst.txt  |    2 +-
 .../deploy_object_detection_pytorch.rst.txt        |    4 +-
 .../deploy_models/deploy_prequantized.rst.txt      |    6 +-
 .../deploy_prequantized_tflite.rst.txt             |    4 +-
 .../how_to/deploy_models/deploy_quantized.rst.txt  |    2 +-
 .../deploy_models/deploy_ssd_gluoncv.rst.txt       |    4 +-
 .../deploy_models/sg_execution_times.rst.txt       |   18 +-
 .../extend_tvm/bring_your_own_datatypes.rst.txt    |    2 +-
 .../how_to/extend_tvm/sg_execution_times.rst.txt   |   10 +-
 .../how_to/extend_tvm/use_pass_instrument.rst.txt  |   16 +-
 .../optimize_operators/opt_conv_cuda.rst.txt       |    2 +-
 .../optimize_operators/opt_conv_tensorcore.rst.txt |    2 +-
 .../how_to/optimize_operators/opt_gemm.rst.txt     |   16 +-
 .../optimize_operators/sg_execution_times.rst.txt  |    8 +-
 .../sg_execution_times.rst.txt                     |   14 +-
 .../tune_conv2d_layer_cuda.rst.txt                 | 2285 ++++++++++++++++++--
 .../tune_network_cuda.rst.txt                      |    2 +-
 .../tune_network_x86.rst.txt                       |    4 +-
 .../tune_sparse_x86.rst.txt                        |   84 +-
 .../tune_with_autotvm/sg_execution_times.rst.txt   |    8 +-
 .../tune_with_autotvm/tune_conv2d_cuda.rst.txt     |   26 +-
 .../work_with_microtvm/micro_autotune.rst.txt      |   16 +-
 .../how_to/work_with_microtvm/micro_train.rst.txt  |   16 +-
 .../work_with_microtvm/sg_execution_times.rst.txt  |   10 +-
 .../work_with_relay/sg_execution_times.rst.txt     |    8 +-
 .../how_to/work_with_schedules/intrin_math.rst.txt |    2 +-
 .../work_with_schedules/sg_execution_times.rst.txt |   14 +-
 .../how_to/work_with_schedules/tensorize.rst.txt   |    2 +-
 .../tutorials/autotvm/sg_execution_times.rst.txt   |    4 +-
 .../frontend/deploy_classification.rst.txt         |    2 +-
 .../tutorials/frontend/deploy_detection.rst.txt    |    2 +-
 .../tutorials/frontend/sg_execution_times.rst.txt  |    6 +-
 .../tutorials/optimize/sg_execution_times.rst.txt  |    6 +-
 .../topic/vta/tutorials/sg_execution_times.rst.txt |    6 +-
 .../tutorial/auto_scheduler_matmul_x86.rst.txt     |    7 +-
 docs/_sources/tutorial/autotvm_matmul_x86.rst.txt  |   20 +-
 docs/_sources/tutorial/autotvm_relay_x86.rst.txt   |   54 +-
 .../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       |   45 +-
 docs/commit_hash                                   |    2 +-
 docs/genindex.html                                 |   12 +-
 docs/how_to/compile_models/from_darknet.html       |    1 +
 docs/how_to/compile_models/from_mxnet.html         |    2 +-
 docs/how_to/compile_models/from_oneflow.html       |   12 +-
 docs/how_to/compile_models/from_pytorch.html       |    6 +-
 docs/how_to/compile_models/from_tensorflow.html    |    2 +-
 docs/how_to/compile_models/sg_execution_times.html |   30 +-
 .../deploy_models/deploy_model_on_android.html     |    2 +-
 .../deploy_object_detection_pytorch.html           |   43 +-
 docs/how_to/deploy_models/deploy_prequantized.html |    8 +-
 .../deploy_models/deploy_prequantized_tflite.html  |    4 +-
 docs/how_to/deploy_models/deploy_quantized.html    |    2 +-
 docs/how_to/deploy_models/deploy_ssd_gluoncv.html  |   38 +-
 docs/how_to/deploy_models/sg_execution_times.html  |   18 +-
 .../extend_tvm/bring_your_own_datatypes.html       |    2 +-
 docs/how_to/extend_tvm/sg_execution_times.html     |   10 +-
 docs/how_to/extend_tvm/use_pass_instrument.html    |   16 +-
 docs/how_to/optimize_operators/opt_conv_cuda.html  |    2 +-
 .../optimize_operators/opt_conv_tensorcore.html    |    2 +-
 docs/how_to/optimize_operators/opt_gemm.html       |   16 +-
 .../optimize_operators/sg_execution_times.html     |    8 +-
 .../sg_execution_times.html                        |   14 +-
 .../tune_conv2d_layer_cuda.html                    | 2285 ++++++++++++++++++--
 .../tune_with_autoscheduler/tune_network_cuda.html |    2 +-
 .../tune_with_autoscheduler/tune_network_x86.html  |    4 +-
 .../tune_with_autoscheduler/tune_sparse_x86.html   |   84 +-
 .../tune_with_autotvm/sg_execution_times.html      |    8 +-
 .../how_to/tune_with_autotvm/tune_conv2d_cuda.html |   26 +-
 docs/how_to/work_with_microtvm/micro_autotune.html |   16 +-
 docs/how_to/work_with_microtvm/micro_train.html    |   16 +-
 .../work_with_microtvm/sg_execution_times.html     |   10 +-
 .../how_to/work_with_relay/sg_execution_times.html |    8 +-
 docs/how_to/work_with_schedules/intrin_math.html   |    2 +-
 .../work_with_schedules/sg_execution_times.html    |   14 +-
 docs/how_to/work_with_schedules/tensorize.html     |    2 +-
 docs/install/nnpack.html                           |   12 +-
 docs/objects.inv                                   |  Bin 23374 -> 23404 bytes
 docs/reference/api/python/auto_scheduler.html      |    4 +-
 docs/reference/api/python/tir.html                 |   97 +
 .../api/typedoc/classes/bytestreamreader.html      |   12 +-
 .../api/typedoc/classes/cachedcallstack.html       |   34 +-
 docs/reference/api/typedoc/classes/dldatatype.html |   12 +-
 docs/reference/api/typedoc/classes/dldevice.html   |   10 +-
 .../reference/api/typedoc/classes/environment.html |   12 +-
 docs/reference/api/typedoc/classes/ffilibrary.html |   20 +-
 .../api/typedoc/classes/graphexecutor.html         |   16 +-
 docs/reference/api/typedoc/classes/instance.html   |   40 +-
 docs/reference/api/typedoc/classes/memory.html     |   34 +-
 docs/reference/api/typedoc/classes/module.html     |   10 +-
 docs/reference/api/typedoc/classes/ndarray.html    |   22 +-
 .../api/typedoc/classes/packedfunccell.html        |    6 +-
 docs/reference/api/typedoc/classes/rpcserver.html  |   14 +-
 docs/reference/api/typedoc/classes/scalar.html     |    6 +-
 .../api/typedoc/classes/webgpucontext.html         |   12 +-
 docs/reference/api/typedoc/enums/argtypecode.html  |   30 +-
 .../api/typedoc/enums/aynccallbackcode.html        |    4 +-
 .../api/typedoc/enums/dldatatypecode.html          |    8 +-
 .../api/typedoc/enums/rpcserverstate.html          |   12 +-
 docs/reference/api/typedoc/enums/sizeof.html       |   18 +-
 docs/reference/api/typedoc/index.html              |  112 +-
 .../api/typedoc/interfaces/disposable.html         |    2 +-
 .../api/typedoc/interfaces/functioninfo.html       |    6 +-
 .../api/typedoc/interfaces/libraryprovider.html    |    4 +-
 docs/searchindex.js                                |    2 +-
 .../vta/tutorials/autotvm/sg_execution_times.html  |    4 +-
 .../tutorials/frontend/deploy_classification.html  |    2 +-
 .../vta/tutorials/frontend/deploy_detection.html   |    2 +-
 .../vta/tutorials/frontend/sg_execution_times.html |    6 +-
 .../vta/tutorials/optimize/sg_execution_times.html |    6 +-
 docs/topic/vta/tutorials/sg_execution_times.html   |    6 +-
 docs/tutorial/auto_scheduler_matmul_x86.html       |    3 +-
 docs/tutorial/autotvm_matmul_x86.html              |   20 +-
 docs/tutorial/autotvm_relay_x86.html               |  258 +--
 docs/tutorial/cross_compilation_and_rpc.html       |    2 +-
 docs/tutorial/intro_topi.html                      |    2 +-
 docs/tutorial/sg_execution_times.html              |   28 +-
 docs/tutorial/tensor_expr_get_started.html         |   41 +-
 125 files changed, 5285 insertions(+), 1197 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 b72ddc1d2..13be3c4ee 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -315,6 +315,11 @@ The process is no different from other examples.
 
 
 
+.. rst-class:: sphx-glr-timing
+
+   **Total running time of the script:** ( 1 minutes  6.401 seconds)
+
+
 .. _sphx_glr_download_how_to_compile_models_from_darknet.py:
 
 .. only:: html
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 a1552a7cf..0129509e5 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -115,7 +115,7 @@ In this section, we download a pretrained imagenet model and classify an image.
 
  .. code-block:: none
 
-    Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipa97be0da-0169-4616-8f5c-a2d16f3b792d from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+    Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip24111cca-40d1-49e3-a31c-1ffdd1f8de77 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 65e64af25..097104914 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -113,7 +113,7 @@ Load a pretrained OneFlow model and save model
  .. code-block:: none
 
     Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
      0%|          | 0.00/41.5M [00:00<?, ?B/s]
     15%|#5        | 6.33M/41.5M [00:00<00:00, 59.9MB/s]
     35%|###4      | 14.3M/41.5M [00:00<00:00, 48.0MB/s]
     46%|####6     | 19.1M/41.5M [00:00<00:00, 45.9MB/s]
     58%|#####7    | 24.0M/41.5M [00:00<00:00, 46.4MB/s]
     77%|#######7  | 32.1M/41.5M [00:00<00:00, 53.4MB/s]
    100%|##########| 41.5M/41.5M [00:00<00:00, 58.0MB/s]
+
      0%|          | 0.00/41.5M [00:00<?, ?B/s]
     19%|#9        | 7.99M/41.5M [00:00<00:00, 52.0MB/s]
     39%|###8      | 16.0M/41.5M [00:00<00:00, 50.5MB/s]
     57%|#####7    | 23.8M/41.5M [00:00<00:00, 60.9MB/s]
     72%|#######2  | 29.9M/41.5M [00:00<00:00, 60.5MB/s]
     87%|########6 | 35.9M/41.5M [00:00<00:00, 43.3MB/s]
    100%|##########| 41.5M/41.5M [00:00<00:00, 50.2MB/s]
 
 
 
diff --git a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
index 68adf074d..8b05a5dc6 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -94,7 +94,7 @@ Load a pretrained PyTorch model
  .. code-block:: none
 
     Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
-
      0%|          | 0.00/44.7M [00:00<?, ?B/s]
     37%|###6      | 16.4M/44.7M [00:00<00:00, 172MB/s]
     88%|########8 | 39.4M/44.7M [00:00<00:00, 212MB/s]
    100%|##########| 44.7M/44.7M [00:00<00:00, 212MB/s]
+
      0%|          | 0.00/44.7M [00:00<?, ?B/s]
     38%|###7      | 16.8M/44.7M [00:00<00:00, 176MB/s]
     82%|########1 | 36.4M/44.7M [00:00<00:00, 194MB/s]
    100%|##########| 44.7M/44.7M [00:00<00:00, 186MB/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 b0bb8b56d..100b90413 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -423,7 +423,7 @@ Run the corresponding model on tensorflow
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  1.023 seconds)
+   **Total running time of the script:** ( 1 minutes  4.461 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 9946a3a45..adf2da219 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
 =================
-**04:53.309** total execution time for **how_to_compile_models** files:
+**05:15.248** total execution time for **how_to_compile_models** files:
 
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:01.023 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)       | 01:06.401 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)       | 00:59.281 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:04.461 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)         | 00:38.293 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)         | 00:41.004 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)       | 00:27.333 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)       | 00:29.429 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)           | 00:24.496 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)         | 00:26.212 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)         | 00:24.217 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)           | 00:25.790 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)         | 00:21.478 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)         | 00:23.010 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)       | 00:19.442 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)       | 00:20.545 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)           | 00:15.434 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)           | 00:15.918 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)             | 00:02.310 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)             | 00:02.479 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
index 5c5663c83..eb2c91ef6 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
@@ -441,7 +441,7 @@ Execute on TVM
     Evaluate inference time cost...
     Execution time summary:
      mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)  
-      16.3936      16.6600      16.9417      15.6985       0.4797   
+      16.2030      16.2295      16.4214      15.9420       0.1322   
                
 
 
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 fefa09c96..23497f1cf 100644
--- a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
@@ -123,7 +123,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
  .. code-block:: none
 
     Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
      0%|          | 0.00/170M [00:00<?, ?B/s]
      2%|2         | 3.47M/170M [00:00<00:04, 36.1MB/s]
      4%|4         | 7.09M/170M [00:00<00:04, 37.2MB/s]
     21%|##1       | 35.7M/170M [00:00<00:00, 157MB/s] 
     33%|###3      | 56.5M/170M [00:00<00:00, 181MB/s]
     48%|####7     | 81.2M/170M [00:00<00:00, 209MB/s]
     62%|######2   | 106M/170M [00:00<00:00, 225MB/s] 
     78%|#######7  | 132M/170M [00:00<00:00, 243MB/s]
     94%|#########3| 159M/170M [00:00<00:00, 254MB/s]
    100%|##########| 170M/170M [00:00<00:00, 210MB/s]
+
      0%|          | 0.00/170M [00:00<?, ?B/s]
      3%|3         | 5.67M/170M [00:00<00:02, 59.4MB/s]
      7%|6         | 11.3M/170M [00:00<00:02, 58.7MB/s]
     10%|9         | 16.9M/170M [00:00<00:03, 51.4MB/s]
     13%|#3        | 22.6M/170M [00:00<00:02, 54.2MB/s]
     16%|#6        | 27.9M/170M [00:00<00:02, 54.8MB/s]
     20%|#9        | 33.7M/170M [00:00<00:02, 56.6MB/s]
     23%|##3       | 39.9M/170M [00:00<00:02, 59.3MB/s]
     27%|##6       | 45.6M/170M [00:00<00:02, 56.4MB/s]
     30%|###       | 51.0M/170M [00:01<00:02, 47.4MB/s]
     34%|###3      | 57.0M/170M [00:01<00:02, 51.3MB/s]
     37%|###6      | 62.5M/170M [00:01<00:02, 52.9MB/s]
     40%|####      | 68.5M/170M [00:01<00:01, 55.3MB/s]
     44%|####3     | 74.0M/170M [00:01<00:01, 55.6MB/s]
     47%|####6     | 79.4M/170M [00:01<00:01, 53.3MB/s]
     50%|####9     | 84.6M/170M [00:01<00:01, 50.6MB/s]
     53%|#####3    | 90.2M/170M [00:01<00:01, 53.1MB/s]
     56%|#####6    | 95.5M/170M [00:01<00:01, 53.5MB/
 s]
     59%|#####9    | 101M/170M [00:01<00:01, 53.6MB/s] 
     63%|######2   | 107M/170M [00:02<00:01, 56.2MB/s]
     66%|######5   | 112M/170M [00:02<00:01, 56.4MB/s]
     69%|######9   | 118M/170M [00:02<00:00, 58.1MB/s]
     73%|#######2  | 124M/170M [00:02<00:00, 54.6MB/s]
     76%|#######5  | 129M/170M [00:02<00:00, 55.0MB/s]
     79%|#######9  | 134M/170M [00:02<00:00, 50.0MB/s]
     82%|########1 | 139M/170M [00:02<00:00, 42.7MB/s]
     84%|########4 | 143M/170M [00:02<00:00, 41.6MB/s]
     87%|########6 | 148M/170M [00:03<00:00, 40.4MB/s]
     89%|########9 | 152M/170M [00:03<00:00, 37.9MB/s]
     93%|#########2| 157M/170M [00:03<00:00, 43.3MB/s]
     96%|#########5| 162M/170M [00:03<00:00, 46.3MB/s]
     98%|#########8| 167M/170M [00:03<00:00, 43.3MB/s]
    100%|##########| 170M/170M [00:03<00:00, 49.6MB/s]
     /usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
       for i in range(dim)
     /usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -292,7 +292,7 @@ Get boxes with score larger than 0.9
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 2 minutes  51.184 seconds)
+   **Total running time of the script:** ( 3 minutes  7.822 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 e99bf70d5..7089d09d9 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -232,7 +232,7 @@ training. Other models require a full post training calibration.
  .. code-block:: none
 
     Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
      0%|          | 0.00/13.6M [00:00<?, ?B/s]
    100%|##########| 13.6M/13.6M [00:00<00:00, 186MB/s]
+
      0%|          | 0.00/13.6M [00:00<?, ?B/s]
     26%|##6       | 3.54M/13.6M [00:00<00:00, 31.2MB/s]
     63%|######2   | 8.49M/13.6M [00:00<00:00, 42.5MB/s]
    100%|##########| 13.6M/13.6M [00:00<00:00, 58.6MB/s]
 
 
 
@@ -412,7 +412,7 @@ Here we give an example of how to measure performance of TVM compiled models.
 
     Execution time summary:
      mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)  
-      90.1168      90.0889      91.4455      89.8083       0.2969   
+      90.4677      90.3767      94.2328      90.0733       0.5179   
                
 
 
@@ -461,7 +461,7 @@ TODO
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  7.102 seconds)
+   **Total running time of the script:** ( 1 minutes  11.881 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 af96f9b44..e85d2a082 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
@@ -439,7 +439,7 @@ Here we give an example of how to measure performance of TVM compiled models.
 
     Execution time summary:
      mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)  
-      119.6067     119.3060     146.4217     117.5544      2.7795   
+      121.3751     121.3598     122.9928     120.4364      0.3941   
                
 
 
@@ -476,7 +476,7 @@ Here we give an example of how to measure performance of TVM compiled models.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 2 minutes  0.237 seconds)
+   **Total running time of the script:** ( 2 minutes  1.613 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 232823e2c..8a246dc46 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -255,7 +255,7 @@ We create a Relay VM to build and execute the model.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  15.268 seconds)
+   **Total running time of the script:** ( 1 minutes  43.351 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 b3b0dc85d..3aa7eabc7 100644
--- a/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
@@ -158,7 +158,7 @@ Convert and compile model for CPU.
             data: None
       input_sym_arg_type = in_param.infer_type()[0]
     Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
      0%|          | 0/132723 [00:00<?, ?KB/s]
      4%|4         | 5617/132723 [00:00<00:02, 56166.71KB/s]
     10%|#         | 13279/132723 [00:00<00:01, 68192.35KB/s]
     16%|#5        | 20877/132723 [00:00<00:01, 71745.92KB/s]
     21%|##1       | 28527/132723 [00:00<00:01, 73619.45KB/s]
     27%|##7       | 36242/132723 [00:00<00:01, 74890.16KB/s]
     33%|###3      | 43904/132723 [00:00<00:01, 75474.81KB/s]
     39%|###8      | 51553/132723 [00:00<00:01, 75805.16KB/s]
     45%|####4     | 59294/132723 [00:00<00:00, 76311.77KB/s]
     50%|#####     | 66993/132723 [00:00<00:00, 76522.43KB/s]
     56%|#####6    | 74717/132723 [00:01<00:00, 76740.24KB/s]
     62%|######2   | 82392/132723 [00:01<00:00, 76545.10KB/s]
     68%|######7   | 90061/132723 [00:01<00:00, 76585.24KB/s]
     74%|#######3  | 98083/132723 [00:01<00:00, 77683.44KB/s]
     80%|########  | 106591/132723 [00:01<00:00, 79912.95KB/s]
     87%|########6 | 115060/132723 [00:01<00:00, 81350.55KB/s]
     93%|#########
 3| 123490/132723 [00:01<00:00, 82235.51KB/s]
     99%|#########9| 131951/132723 [00:01<00:00, 82943.63KB/s]
    100%|##########| 132723/132723 [00:01<00:00, 77510.05KB/s]
+
      0%|          | 0/132723 [00:00<?, ?KB/s]
      4%|3         | 5015/132723 [00:00<00:02, 50145.86KB/s]
      9%|9         | 12478/132723 [00:00<00:01, 64545.76KB/s]
     15%|#5        | 20057/132723 [00:00<00:01, 69678.07KB/s]
     21%|##        | 27505/132723 [00:00<00:01, 71570.54KB/s]
     26%|##6       | 35103/132723 [00:00<00:01, 73159.43KB/s]
     32%|###2      | 42576/132723 [00:00<00:01, 73691.34KB/s]
     38%|###7      | 50113/132723 [00:00<00:01, 74238.16KB/s]
     43%|####3     | 57695/132723 [00:00<00:01, 74738.45KB/s]
     49%|####9     | 65245/132723 [00:00<00:00, 74975.47KB/s]
     55%|#####4    | 72791/132723 [00:01<00:00, 75122.58KB/s]
     61%|######    | 80304/132723 [00:01<00:00, 75057.07KB/s]
     66%|######6   | 87857/132723 [00:01<00:00, 75194.98KB/s]
     72%|#######1  | 95515/132723 [00:01<00:00, 75612.66KB/s]
     78%|#######7  | 103077/132723 [00:01<00:00, 75276.44KB/s]
     83%|########3 | 110627/132723 [00:01<00:00, 75341.67KB/s]
     89%|########9
  | 118238/132723 [00:01<00:00, 75571.06KB/s]
     95%|#########4| 125813/132723 [00:01<00:00, 75621.12KB/s]
    100%|##########| 132723/132723 [00:01<00:00, 73993.14KB/s]
 
 
 
@@ -241,7 +241,7 @@ Display result
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 2 minutes  35.161 seconds)
+   **Total running time of the script:** ( 2 minutes  40.989 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 377ea84b4..e56b13e0e 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
@@ -5,24 +5,24 @@
 
 Computation times
 =================
-**11:02.842** total execution time for **how_to_deploy_models** files:
+**12:02.548** total execution time for **how_to_deploy_models** files:
 
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 02:51.184 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:07.822 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)                           | 02:35.161 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)                           | 02:40.989 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)           | 02:00.237 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)           | 02:01.613 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)                               | 01:15.268 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)                               | 01:43.351 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)                         | 01:07.102 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)                         | 01:11.881 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)                 | 00:28.951 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)                 | 00:30.443 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``)                       | 00:22.704 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``)                       | 00:23.438 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)                       | 00:22.230 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)                       | 00:23.004 | 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 8d6ad2668..41bcbf041 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.zip4f61c6d4-1303-47fa-a368-340a17a98374 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+    Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip6f76c4cb-29f9-46ef-a272-c0c11b644acf 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 5906ab272..5c50074c0 100644
--- a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
 
 Computation times
 =================
-**00:40.510** total execution time for **how_to_extend_tvm** files:
+**00:42.886** total execution time for **how_to_extend_tvm** files:
 
 +-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:37.382 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:39.644 | 0.0 MB |
 +-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)           | 00:02.202 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)           | 00:02.279 | 0.0 MB |
 +-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)                     | 00:00.918 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)                     | 00:00.956 | 0.0 MB |
 +-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``)       | 00:00.009 | 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 5b375134a..ac1c8b3ec 100644
--- a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
@@ -216,10 +216,10 @@ profile the execution time of each passes.
  .. code-block:: none
 
     Printing results of timing profile...
-    InferType: 6778us [6778us] (46.27%; 46.27%)
-    FoldScaleAxis: 7869us [6us] (53.73%; 53.73%)
-            FoldConstant: 7864us [1632us] (53.69%; 99.93%)
-                    InferType: 6232us [6232us] (42.54%; 79.25%)
+    InferType: 6794us [6794us] (46.09%; 46.09%)
+    FoldScaleAxis: 7947us [5us] (53.91%; 53.91%)
+            FoldConstant: 7941us [1649us] (53.87%; 99.93%)
+                    InferType: 6292us [6292us] (42.69%; 79.23%)
 
 
 
@@ -258,10 +258,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
  .. code-block:: none
 
     Printing results of timing profile...
-    InferType: 6256us [6256us] (44.66%; 44.66%)
-    FoldScaleAxis: 7752us [5us] (55.34%; 55.34%)
-            FoldConstant: 7747us [1607us] (55.30%; 99.94%)
-                    InferType: 6140us [6140us] (43.83%; 79.25%)
+    InferType: 6344us [6344us] (43.25%; 43.25%)
+    FoldScaleAxis: 8325us [4us] (56.75%; 56.75%)
+            FoldConstant: 8320us [1641us] (56.72%; 99.95%)
+                    InferType: 6680us [6680us] (45.54%; 80.28%)
 
 
 
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 0c11a51cc..895168bfd 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
@@ -340,7 +340,7 @@ latency of convolution.
 
  .. code-block:: none
 
-    Convolution: 52.792715 ms
+    Convolution: 48.048866 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 a1e8499a7..3a8525661 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
@@ -671,7 +671,7 @@ be able to run on our build server
 
  .. code-block:: none
 
-    conv2d with tensor core: 9.696405 ms
+    conv2d with tensor core: 9.910798 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 cfe39516a..4bedf941a 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -143,8 +143,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
 
  .. code-block:: none
 
-    Numpy running time: 0.018475
-    Baseline: 3.207243
+    Numpy running time: 0.019208
+    Baseline: 3.461791
 
 
 
@@ -239,7 +239,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
 
  .. code-block:: none
 
-    Opt1: 0.310522
+    Opt1: 0.318913
 
 
 
@@ -342,7 +342,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
 
  .. code-block:: none
 
-    Opt2: 0.344958
+    Opt2: 0.349989
 
 
 
@@ -438,7 +438,7 @@ the access pattern for A matrix is more cache friendly.
 
  .. code-block:: none
 
-    Opt3: 0.115670
+    Opt3: 0.121454
 
 
 
@@ -563,7 +563,7 @@ flattening.
 
  .. code-block:: none
 
-    Opt4: 0.109684
+    Opt4: 0.109826
 
 
 
@@ -685,7 +685,7 @@ write to C when all the block results are ready.
 
  .. code-block:: none
 
-    Opt5: 0.110460
+    Opt5: 0.110997
 
 
 
@@ -810,7 +810,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
 
  .. code-block:: none
 
-    Opt6: 0.146852
+    Opt6: 0.147262
 
 
 
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 2952d81ae..b5418a283 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
 
 Computation times
 =================
-**00:34.120** total execution time for **how_to_optimize_operators** files:
+**00:35.432** total execution time for **how_to_optimize_operators** files:
 
 +-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)                       | 00:31.872 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)                       | 00:32.965 | 0.0 MB |
 +-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.237 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.357 | 0.0 MB |
 +-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)             | 00:01.011 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)             | 00:01.110 | 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 3486bd2d6..f88f46cf8 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
 =================
-**05:59.708** total execution time for **how_to_tune_with_autoscheduler** files:
+**06:11.482** total execution time for **how_to_tune_with_autoscheduler** files:
 
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 03:15.021 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 03:22.385 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)             | 01:21.767 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)             | 01:23.952 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)           | 00:46.378 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)           | 00:47.473 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)               | 00:19.391 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)               | 00:19.683 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)           | 00:08.706 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)           | 00:09.068 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)             | 00:08.447 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)             | 00:08.920 | 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 1fd37cc4c..06701f960 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
@@ -240,102 +240,1118 @@ cooperative fetching, unrolling and operator fusion.
                  compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
       buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
       preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
-      attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 32;
-      allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
-      allocate(pad_temp.shared: Pointer(shared float32), float32, [162]), storage_scope = shared;
-      allocate(kernel.shared: Pointer(shared float32), float32, [288]), storage_scope = shared;
+      attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
+      allocate(conv2d_nchw: Pointer(local float32), float32, [28]), storage_scope = local;
+      allocate(pad_temp.shared: Pointer(shared float32), float32, [324]), storage_scope = shared;
+      allocate(kernel.shared: Pointer(shared float32), float32, [1152]), storage_scope = shared;
       attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
-        conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
+        conv2d_nchw_1: Buffer(conv2d_nchw, float32, [196], [], scope="local", align=32)[0] = 0f32
+        conv2d_nchw_1[14] = 0f32
         conv2d_nchw_1[1] = 0f32
+        conv2d_nchw_1[15] = 0f32
         conv2d_nchw_1[2] = 0f32
+        conv2d_nchw_1[16] = 0f32
         conv2d_nchw_1[3] = 0f32
+        conv2d_nchw_1[17] = 0f32
         conv2d_nchw_1[4] = 0f32
+        conv2d_nchw_1[18] = 0f32
         conv2d_nchw_1[5] = 0f32
+        conv2d_nchw_1[19] = 0f32
         conv2d_nchw_1[6] = 0f32
+        conv2d_nchw_1[20] = 0f32
         conv2d_nchw_1[7] = 0f32
+        conv2d_nchw_1[21] = 0f32
         conv2d_nchw_1[8] = 0f32
+        conv2d_nchw_1[22] = 0f32
         conv2d_nchw_1[9] = 0f32
+        conv2d_nchw_1[23] = 0f32
         conv2d_nchw_1[10] = 0f32
+        conv2d_nchw_1[24] = 0f32
         conv2d_nchw_1[11] = 0f32
+        conv2d_nchw_1[25] = 0f32
         conv2d_nchw_1[12] = 0f32
+        conv2d_nchw_1[26] = 0f32
         conv2d_nchw_1[13] = 0f32
-        for (rc.outer.outer: int32, 0, 256) {
-          let cse_var_2: int32 = (rc.outer.outer*98)
-          let cse_var_1: int32 = (rc.outer.outer*18)
+        conv2d_nchw_1[27] = 0f32
+        for (rc.outer.outer: int32, 0, 128) {
+          let cse_var_2: int32 = (rc.outer.outer*196)
+          let cse_var_1: int32 = (rc.outer.outer*36)
            {
             attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
-            pad_temp.shared_1: Buffer(pad_temp.shared, float32, [162], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((9 <= threadIdx.x_1) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[(((cse_var_2 + (floordiv(threadIdx.x_1, 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+            pad_temp.shared_1: Buffer(pad_temp.shared, float32, [324], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((9 <= threadIdx.x_1) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[(((cse_var_2 + (floordiv(threadIdx.x_1, 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
             attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
             pad_temp.shared_1[(threadIdx.x_1 + 56)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 56), 81)) && (floormod((threadIdx.x_1 + 56), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 56), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 56), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
             attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
-            if @tir.likely((threadIdx.x_1 < 50), dtype=bool) {
-              pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else((((threadIdx.x_1 < 41) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 112), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 31), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+            pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 31), 81)) && (floormod((threadIdx.x_1 + 31), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 112), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 31), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+            attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+            pad_temp.shared_1[(threadIdx.x_1 + 168)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 6), 81)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 168), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 6), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+            attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+            pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 62), 81)) && (floormod((threadIdx.x_1 + 62), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 62), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+            attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+            if @tir.likely((threadIdx.x_1 < 44), dtype=bool) {
+              pad_temp.shared_1[(threadIdx.x_1 + 280)] = @tir.if_then_else((((threadIdx.x_1 < 35) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 280), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 37), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
             }
             attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
-            kernel.shared_1: Buffer(kernel.shared, float32, [288], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 18))]
+            kernel.shared_1: Buffer(kernel.shared, float32, [1152], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 36)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 36))]
             attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
-            kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 56), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 18))]
+            kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 56), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 36), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
             attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
-            kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 112), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 18))]
+            kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 36)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 36))]
             attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
-            kernel.shared_1[(threadIdx.x_2 + 168)] = kernel[((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 168), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 6), 18))]
+            kernel.shared_1[(threadIdx.x_2 + 168)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 168), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 24), 36), 9)*9)) + floormod((threadIdx.x_2 + 6), 9))]
             attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
-            kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 224), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 18))]
+            kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 36)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 36))]
             attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
-            if @tir.likely((threadIdx.x_2 < 8), dtype=bool) {
-              kernel.shared_1[(threadIdx.x_2 + 280)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 280), 18)*4608)) + cse_var_1) + threadIdx.x_2) + 10)]
-            }
-            for (rc.outer.inner: int32, 0, 2) {
-              for (ry.outer.inner: int32, 0, 3) {
-                conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3))]))
-                conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3))]))
-                conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3))]))
-                conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3))]))
-                conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3))]))
-                conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3))]))
-                conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3))]))
-                conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 18)]))
-                conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 18)]))
-                conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 18)]))
-                conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 18)]))
-                conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 18)]))
-                conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 18)]))
-                conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 18)]))
-                conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 1)]))
-                conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 1)]))
-                conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 1)]))
-                conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 1)]))
-                conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 1)]))
-                conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 1)]))
-                conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 1)]))
-                conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 19)]))
-                conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 19)]))
-                conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 19)]))
-                conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 19)]))
-                conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 19)]))
-                conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 19)]))
-                conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 19)]))
-                conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 2)]))
-                conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 2)]))
-                conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 2)]))
-                conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 2)]))
-                conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 2)]))
-                conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 2)]))
-                conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 2)]))
-                conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 20)]))
-                conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 20)]))
-                conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 20)]))
-                conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 20)]))
-                conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 20)]))
-                conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 20)]))
-                conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 20)]))
-              }
+            kernel.shared_1[(threadIdx.x_2 + 280)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 280), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 28), 36), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+            kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 12), 36), 9)*9)) + floormod((threadIdx.x_2 + 3), 9))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+            kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 392), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 36), 9)*9)) + floormod((threadIdx.x_2 + 5), 9))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+            kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 36), 9)*9)) + floormod((threadIdx.x_2 + 7), 9))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+            kernel.shared_1[(threadIdx.x_2 + 504)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 36)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 36)) + 64512)]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+            kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 36), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+            kernel.shared_1[(threadIdx.x_2 + 616)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 616), 36)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 36))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+            kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 672), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 24), 36), 9)*9)) + floormod((threadIdx.x_2 + 6), 9))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+            kernel.shared_1[(threadIdx.x_2 + 728)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 728), 36)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 36))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+            kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 784), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 28), 36), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+            kernel.shared_1[(threadIdx.x_2 + 840)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 840), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 12), 36), 9)*9)) + floormod((threadIdx.x_2 + 3), 9))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+            kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 896), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 36), 9)*9)) + floormod((threadIdx.x_2 + 5), 9))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+            kernel.shared_1[(threadIdx.x_2 + 952)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 952), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 36), 9)*9)) + floormod((threadIdx.x_2 + 7), 9))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+            kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 36)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 36)) + 129024)]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+            kernel.shared_1[(threadIdx.x_2 + 1064)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1064), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 36), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+            if @tir.likely((threadIdx.x_2 < 32), dtype=bool) {
+              kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1120), 36)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 36))]
             }
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 7)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
+            conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[floormod(threadIdx.x, 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 576)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 9)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
+            conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 576)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
+            conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 576)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
+            conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 576)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
+            conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 576)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
+            conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 576)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
+            conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 576)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
+            conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 577)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
+            conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 577)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
+            conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 577)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
+            conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 577)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
+            conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 577)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
+            conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 577)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
+            conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 577)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
+            conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 578)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
+            conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 578)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
+            conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 578)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
+            conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 578)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
+            conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 578)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
+            conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 578)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
+            conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 578)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[floormod(threadIdx.x, 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
+            conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[floormod(threadIdx.x, 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 612)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
+            conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 612)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
+            conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 612)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
+            conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 612)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
+            conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 612)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
+            conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 612)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
+            conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 612)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
+            conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 613)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
+            conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 613)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
+            conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 613)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
+            conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 613)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
+            conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 613)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
+            conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 613)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
+            conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 613)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
+            conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 614)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
+            conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 614)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
+            conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 614)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
+            conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 614)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
+            conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 614)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
+            conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 614)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
+            conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 614)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
+            conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 579)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
+            conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 579)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
+            conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 579)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
+            conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 579)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
+            conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 579)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
+            conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 579)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
+            conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 579)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
+            conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 580)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
+            conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 580)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
+            conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 580)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
+            conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 580)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
+            conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 580)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
+            conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 580)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
+            conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 580)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
+            conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 581)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
+            conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 581)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
+            conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 581)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
+            conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 581)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
+            conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 581)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
+            conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 581)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
+            conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 581)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
+            conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 615)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
+            conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 615)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
+            conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 615)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
+            conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 615)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
+            conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 615)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
+            conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 615)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
+            conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 615)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
+            conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 616)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
+            conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 616)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
+            conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 616)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
+            conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 616)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
+            conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 616)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
+            conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 616)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
+            conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 616)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
+            conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 617)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
+            conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 617)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
+            conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 617)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
+            conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 617)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
+            conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 617)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
+            conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 617)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
+            conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 617)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
+            conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 582)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
+            conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 582)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
+            conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 582)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
+            conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 582)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
+            conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 582)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
+            conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 582)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 72)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
+            conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 72)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 582)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
+            conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 583)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
+            conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 583)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
+            conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 583)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
+            conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 583)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
+            conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 583)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
+            conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 583)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 73)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
+            conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 73)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 583)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
+            conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 584)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
+            conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 584)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
+            conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 584)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
+            conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 584)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
+            conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 584)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
+            conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 584)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 74)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
+            conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 74)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 584)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
+            conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 618)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
+            conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 618)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
+            conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 618)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
+            conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 618)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
+            conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 618)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
+            conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 618)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 72)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
+            conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 72)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 618)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
+            conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 619)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
+            conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 619)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
+            conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 619)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
+            conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 619)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
+            conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 619)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
+            conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 619)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 73)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
+            conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 73)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 619)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
+            conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 620)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
+            conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 620)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
+            conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 620)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
+            conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 620)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
+            conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 620)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
+            conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 620)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 74)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
+            conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 74)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 620)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
+            conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 585)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
+            conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 585)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
+            conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 585)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
+            conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 585)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
+            conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 585)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
+            conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 585)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
+            conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 585)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
+            conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 586)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
+            conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 586)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
+            conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 586)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
+            conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 586)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
+            conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 586)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
+            conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 586)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
+            conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 586)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
+            conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 587)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
+            conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 587)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
+            conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 587)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
+            conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 587)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
+            conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 587)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
+            conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 587)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
+            conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 587)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
+            conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 621)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
+            conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 621)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
+            conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 621)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
+            conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 621)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
+            conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 621)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
+            conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 621)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
+            conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 621)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
+            conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 622)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
+            conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 622)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
+            conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 622)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
+            conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 622)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
+            conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 622)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
+            conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 622)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
+            conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 622)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
+            conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 623)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
+            conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 623)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
+            conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 623)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
+            conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 623)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
+            conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 623)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
+            conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 623)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
+            conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 623)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
+            conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 588)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
+            conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 588)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
+            conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 588)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
+            conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 588)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
+            conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 588)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
+            conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 588)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
+            conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 588)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
+            conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 589)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
+            conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 589)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
+            conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 589)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
+            conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 589)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
+            conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 589)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
+            conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 589)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
+            conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 589)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
+            conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 590)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
+            conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 590)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
+            conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 590)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
+            conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 590)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
+            conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 590)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
+            conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 590)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
+            conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 590)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
+            conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 624)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
+            conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 624)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
+            conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 624)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
+            conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 624)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
+            conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 624)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
+            conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 624)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
+            conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 624)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
+            conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 625)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
+            conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 625)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
+            conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 625)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
+            conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 625)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
+            conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 625)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
+            conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 625)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
+            conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 625)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
+            conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 626)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
+            conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 626)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
+            conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 626)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
+            conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 626)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
+            conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 626)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
+            conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 626)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
+            conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 626)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
+            conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 591)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
+            conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 591)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
+            conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 591)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
+            conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 591)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
+            conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 591)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
+            conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 591)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
+            conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 591)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
+            conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 592)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
+            conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 592)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
+            conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 592)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
+            conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 592)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
+            conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 592)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
+            conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 592)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 154)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
+            conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 154)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 592)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
+            conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 593)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
+            conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 593)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
+            conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 593)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
+            conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 593)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
+            conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 593)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
+            conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 593)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 155)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
+            conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 155)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 593)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
+            conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 627)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
+            conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 627)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
+            conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 627)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
+            conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 627)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
+            conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 627)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
+            conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 627)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
+            conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 627)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
+            conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 628)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
+            conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 628)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
+            conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 628)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
+            conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 628)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
+            conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 628)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
+            conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 628)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 154)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
+            conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 154)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 628)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
+            conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 629)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
+            conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 629)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
+            conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 629)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
+            conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 629)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
+            conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 629)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
+            conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 629)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 155)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
+            conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 155)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 629)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
+            conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 594)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
+            conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 594)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
+            conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 594)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
+            conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 594)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
+            conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 594)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
+            conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 594)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
+            conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 594)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
+            conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 595)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
+            conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 595)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
+            conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 595)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
+            conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 595)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
+            conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 595)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
+            conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 595)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
+            conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 595)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
+            conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 596)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
+            conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 596)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
+            conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 596)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
+            conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 596)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
+            conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 596)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
+            conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 596)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
+            conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 596)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
+            conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 630)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
+            conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 630)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
+            conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 630)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
+            conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 630)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
+            conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 630)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
+            conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 630)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
+            conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 630)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
+            conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 631)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
+            conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 631)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
+            conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 631)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
+            conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 631)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
+            conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 631)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
+            conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 631)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
+            conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 631)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
+            conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 632)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
+            conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 632)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
+            conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 632)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
+            conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 632)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
+            conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 632)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
+            conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 632)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
+            conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 632)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
+            conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 597)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
+            conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 597)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
+            conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 597)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
+            conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 597)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
+            conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 597)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
+            conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 597)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 225)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
+            conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 225)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 597)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
+            conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 598)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
+            conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 598)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
+            conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 598)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
+            conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 598)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
+            conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 598)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
+            conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 598)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 226)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
+            conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 226)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 598)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
+            conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 599)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
+            conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 599)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
+            conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 599)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
+            conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 599)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
+            conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 599)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
+            conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 599)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 227)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
+            conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 227)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 599)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
+            conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 633)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
+            conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 633)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
+            conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 633)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
+            conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 633)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
+            conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 633)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
+            conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 633)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 225)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
+            conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 225)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 633)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
+            conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 634)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
+            conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 634)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
+            conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 634)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
+            conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 634)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
+            conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 634)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
+            conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 634)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 226)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
+            conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 226)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 634)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
+            conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 635)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
+            conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 635)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
+            conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 635)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
+            conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 635)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
+            conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 635)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
+            conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 635)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 227)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
+            conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 227)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 635)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
+            conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 600)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
+            conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 600)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
+            conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 600)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
+            conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 600)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
+            conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 600)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 225)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
+            conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 225)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 600)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 234)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
+            conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 234)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 600)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
+            conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 601)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
+            conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 601)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
+            conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 601)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
+            conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 601)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
+            conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 601)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 226)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
+            conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 226)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 601)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 235)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
+            conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 235)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 601)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
+            conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 602)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
+            conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 602)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
+            conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 602)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
+            conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 602)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
+            conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 602)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 227)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
+            conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 227)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 602)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 236)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
+            conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 236)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 602)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
+            conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 636)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
+            conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 636)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
+            conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 636)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
+            conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 636)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
+            conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 636)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 225)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
+            conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 225)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 636)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 234)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
+            conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 234)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 636)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
+            conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 637)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
+            conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 637)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
+            conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 637)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
+            conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 637)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
+            conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 637)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 226)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
+            conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 226)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 637)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 235)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
+            conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 235)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 637)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
+            conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 638)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
+            conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 638)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
+            conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 638)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
+            conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 638)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
+            conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 638)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 227)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
+            conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 227)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 638)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 236)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
+            conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 236)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 638)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
+            conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 603)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
+            conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 603)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
+            conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 603)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
+            conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 603)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
+            conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 603)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
+            conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 603)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
+            conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 603)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
+            conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 604)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
+            conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 604)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
+            conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 604)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
+            conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 604)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
+            conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 604)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
+            conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 604)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
+            conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 604)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
+            conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 605)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
+            conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 605)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
+            conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 605)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
+            conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 605)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
+            conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 605)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
+            conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 605)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
+            conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 605)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
+            conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 639)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
+            conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 639)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
+            conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 639)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
+            conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 639)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
+            conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 639)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
+            conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 639)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
+            conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 639)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
+            conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 640)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
+            conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 640)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
+            conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 640)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
+            conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 640)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
+            conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 640)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
+            conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 640)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
+            conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 640)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
+            conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 641)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
+            conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 641)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
+            conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 641)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
+            conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 641)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
+            conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 641)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
+            conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 641)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
+            conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 641)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
+            conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 606)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
+            conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 606)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
+            conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 606)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
+            conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 606)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
+            conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 606)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
+            conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 606)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 306)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
+            conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 306)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 606)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
+            conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 607)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
+            conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 607)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
+            conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 607)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
+            conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 607)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
+            conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 607)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
+            conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 607)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 307)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
+            conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 307)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 607)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
+            conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 608)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
+            conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 608)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
+            conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 608)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
+            conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 608)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
+            conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 608)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
+            conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 608)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 308)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
+            conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 308)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 608)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
+            conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 642)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
+            conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 642)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
+            conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 642)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
+            conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 642)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
+            conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 642)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
+            conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 642)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 306)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
+            conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 306)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 642)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
+            conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 643)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
+            conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 643)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
+            conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 643)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
+            conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 643)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
+            conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 643)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
+            conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 643)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 307)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
+            conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 307)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 643)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
+            conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 644)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
+            conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 644)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
+            conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 644)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
+            conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 644)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
+            conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 644)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
+            conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 644)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 308)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
+            conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 308)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 644)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
+            conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 609)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
+            conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 609)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
+            conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 609)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
+            conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 609)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
+            conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 609)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 306)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
+            conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 306)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 609)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 315)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
+            conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 315)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 609)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
+            conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 610)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
+            conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 610)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
+            conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 610)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
+            conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 610)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
+            conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 610)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 307)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
+            conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 307)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 610)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
+            conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 610)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
+            conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 611)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
+            conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 611)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
+            conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 611)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
+            conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 611)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
+            conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 611)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 308)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
+            conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 308)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 611)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
+            conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 611)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
+            conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 645)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
+            conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 645)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
+            conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 645)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
+            conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 645)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
+            conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 645)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 306)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
+            conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 306)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 645)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 315)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
+            conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 315)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 645)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
+            conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 646)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
+            conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 646)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
+            conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 646)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
+            conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 646)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
+            conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 646)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 307)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
+            conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 307)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 646)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
+            conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 646)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
+            conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 647)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
+            conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 647)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
+            conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 647)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
+            conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 647)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
+            conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 647)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 308)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
+            conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 308)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 647)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
+            conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 647)]))
           }
         }
         for (i1.inner: int32, 0, 2) {
           for (i2.inner: int32, 0, 7) {
-            compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[((i1.inner*7) + i2.inner)] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+            let cse_var_3: int32 = ((i1.inner*7) + i2.inner)
+             {
+              compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[cse_var_3] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+              compute[((((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7)) + 784)] = max((conv2d_nchw_1[(cse_var_3 + 14)] + bias[((((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner) + 16)]), 0f32)
+            }
           }
         }
       }
@@ -391,7 +1407,7 @@ We build the binary and check its correctness and performance.
 
  .. code-block:: none
 
-    Execution time of this operator: 0.402 ms
+    Execution time of this operator: 0.378 ms
 
 
 
@@ -439,10 +1455,10 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
     conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
     conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
     conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
-    conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
-    conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
+    conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
+    conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=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=8)
-    conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
+    conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=2)
     conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=7)
     conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
     conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
@@ -452,18 +1468,18 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
     conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
     conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
     conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=1)
-    conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
+    conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
     conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
     conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
-    conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
-    conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+    conv2d_nchw_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=8)
-    compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
+    compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
     compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=7)
     compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
     compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
@@ -495,7 +1511,7 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
     s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
     pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
     s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
-    s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 64)
+    s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
     s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
 
     CUDA source code:
@@ -514,89 +1530,1084 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
       #define uint64_t unsigned long long
     #endif
     extern "C" __global__ void __launch_bounds__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
-      float conv2d_nchw[14];
-      __shared__ float pad_temp_shared[162];
-      __shared__ float kernel_shared[288];
+      float conv2d_nchw[28];
+      __shared__ float pad_temp_shared[324];
+      __shared__ float kernel_shared[1152];
       conv2d_nchw[0] = 0.000000e+00f;
+      conv2d_nchw[14] = 0.000000e+00f;
       conv2d_nchw[1] = 0.000000e+00f;
+      conv2d_nchw[15] = 0.000000e+00f;
       conv2d_nchw[2] = 0.000000e+00f;
+      conv2d_nchw[16] = 0.000000e+00f;
       conv2d_nchw[3] = 0.000000e+00f;
+      conv2d_nchw[17] = 0.000000e+00f;
       conv2d_nchw[4] = 0.000000e+00f;
+      conv2d_nchw[18] = 0.000000e+00f;
       conv2d_nchw[5] = 0.000000e+00f;
+      conv2d_nchw[19] = 0.000000e+00f;
       conv2d_nchw[6] = 0.000000e+00f;
+      conv2d_nchw[20] = 0.000000e+00f;
       conv2d_nchw[7] = 0.000000e+00f;
+      conv2d_nchw[21] = 0.000000e+00f;
       conv2d_nchw[8] = 0.000000e+00f;
+      conv2d_nchw[22] = 0.000000e+00f;
       conv2d_nchw[9] = 0.000000e+00f;
+      conv2d_nchw[23] = 0.000000e+00f;
       conv2d_nchw[10] = 0.000000e+00f;
+      conv2d_nchw[24] = 0.000000e+00f;
       conv2d_nchw[11] = 0.000000e+00f;
+      conv2d_nchw[25] = 0.000000e+00f;
       conv2d_nchw[12] = 0.000000e+00f;
+      conv2d_nchw[26] = 0.000000e+00f;
       conv2d_nchw[13] = 0.000000e+00f;
-      for (int rc_outer_outer = 0; rc_outer_outer < 256; ++rc_outer_outer) {
+      conv2d_nchw[27] = 0.000000e+00f;
+      for (int rc_outer_outer = 0; rc_outer_outer < 128; ++rc_outer_outer) {
         __syncthreads();
-        pad_temp_shared[((int)threadIdx.x)] = ((((9 <= ((int)threadIdx.x)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 98) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
-        pad_temp_shared[(((int)threadIdx.x) + 56)] = (((((9 <= ((((int)threadIdx.x) + 56) % 81)) && (((((int)threadIdx.x) + 56) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 98) + (((((int)threadIdx.x) + 56) / 81) * 49)) + ((((((int)threadIdx.x) + 56) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
-        if (((int)threadIdx.x) < 50) {
-          pad_temp_shared[(((int)threadIdx.x) + 112)] = ((((((int)threadIdx.x) < 41) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 98) + (((((int)threadIdx.x) + 112) / 81) * 49)) + (((((int)threadIdx.x) + 31) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+        pad_temp_shared[((int)threadIdx.x)] = ((((9 <= ((int)threadIdx.x)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+        pad_temp_shared[(((int)threadIdx.x) + 56)] = (((((9 <= ((((int)threadIdx.x) + 56) % 81)) && (((((int)threadIdx.x) + 56) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 56) / 81) * 49)) + ((((((int)threadIdx.x) + 56) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+        pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((9 <= ((((int)threadIdx.x) + 31) % 81)) && (((((int)threadIdx.x) + 31) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 112) / 81) * 49)) + ((((((int)threadIdx.x) + 31) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+        pad_temp_shared[(((int)threadIdx.x) + 168)] = ((((3 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 168) / 81) * 49)) + (((((int)threadIdx.x) + 6) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+        pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((9 <= ((((int)threadIdx.x) + 62) % 81)) && (((((int)threadIdx.x) + 62) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 224) / 81) * 49)) + ((((((int)threadIdx.x) + 62) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+        if (((int)threadIdx.x) < 44) {
+          pad_temp_shared[(((int)threadIdx.x) + 280)] = ((((((int)threadIdx.x) < 35) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 280) / 81) * 49)) + (((((int)threadIdx.x) + 37) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
         }
-        kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 18)) + (((int)threadIdx.x) % 18))];
-        kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 2) % 18))];
-        kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 4) % 18))];
-        kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 168) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 6) % 18))];
-        kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 8) % 18))];
-        if (((int)threadIdx.x) < 8) {
-          kernel_shared[(((int)threadIdx.x) + 280)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 280) / 18) * 4608)) + (rc_outer_outer * 18)) + ((int)threadIdx.x)) + 10)];
+        kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) % 36))];
+        kernel_shared[(((int)threadIdx.x) + 56)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 56) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 20) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
+        kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 4) % 36))];
+        kernel_shared[(((int)threadIdx.x) + 168)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 168) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 24) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 6) % 9))];
+        kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 8) % 36))];
+        kernel_shared[(((int)threadIdx.x) + 280)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 280) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 28) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
+        kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 12) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 3) % 9))];
+        kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 32) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 5) % 9))];
+        kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 16) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 7) % 9))];
+        kernel_shared[(((int)threadIdx.x) + 504)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) % 36)) + 64512)];
+        kernel_shared[(((int)threadIdx.x) + 560)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 20) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
+        kernel_shared[(((int)threadIdx.x) + 616)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 616) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 4) % 36))];
+        kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 672) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 24) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 6) % 9))];
+        kernel_shared[(((int)threadIdx.x) + 728)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 728) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 8) % 36))];
+        kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 28) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
+        kernel_shared[(((int)threadIdx.x) + 840)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 840) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 12) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 3) % 9))];
+        kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 896) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 32) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 5) % 9))];
+        kernel_shared[(((int)threadIdx.x) + 952)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 952) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 16) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 7) % 9))];
+        kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) % 36)) + 129024)];
+        kernel_shared[(((int)threadIdx.x) + 1064)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1064) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 20) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
+        if (((int)threadIdx.x) < 32) {
+          kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1120) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 4))];
         }
         __syncthreads();
-        for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
-          for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
-            conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3))]));
-            conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3))]));
-            conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3))]));
-            conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3))]));
-            conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3))]));
-            conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3))]));
-            conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3))]));
-            conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 18)]));
-            conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 18)]));
-            conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 18)]));
-            conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 18)]));
-            conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 18)]));
-            conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 18)]));
-            conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 18)]));
-            conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 1)]));
-            conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 1)]));
-            conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 1)]));
-            conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 1)]));
-            conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 1)]));
-            conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 1)]));
-            conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 1)]));
-            conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 19)]));
-            conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 19)]));
-            conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 19)]));
-            conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 19)]));
-            conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 19)]));
-            conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 19)]));
-            conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 19)]));
-            conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 2)]));
-            conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 2)]));
-            conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 2)]));
-            conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 2)]));
-            conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 2)]));
-            conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 2)]));
-            conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 2)]));
-            conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 20)]));
-            conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 20)]));
-            conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 20)]));
-            conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 20)]));
-            conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 20)]));
-            conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 20)]));
-            conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 20)]));
-          }
-        }
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 7)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
+        conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((int)threadIdx.x) % 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 576)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
+        conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 576)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
+        conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 576)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
+        conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 576)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
+        conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 576)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
+        conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 576)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
+        conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 576)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
+        conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 577)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
+        conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 577)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
+        conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 577)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
+        conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 577)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
+        conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 577)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
+        conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 577)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
+        conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 577)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
+        conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 578)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
+        conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 578)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
+        conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 578)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
+        conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 578)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
+        conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 578)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
+        conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 578)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
+        conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 578)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) % 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
+        conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((int)threadIdx.x) % 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 612)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
+        conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 612)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
+        conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 612)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
+        conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 612)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
+        conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 612)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
+        conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 612)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
+        conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 612)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
+        conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 613)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
+        conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 613)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
+        conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 613)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
+        conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 613)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
+        conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 613)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
+        conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 613)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
+        conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 613)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
+        conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 614)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
+        conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 614)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
+        conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 614)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
+        conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 614)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
+        conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 614)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
+        conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 614)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
+        conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 614)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
+        conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 579)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
+        conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 579)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
+        conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 579)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
+        conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 579)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
+        conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 579)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
+        conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 579)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
+        conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 579)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
+        conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 580)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
+        conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 580)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
+        conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 580)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
+        conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 580)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
+        conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 580)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
+        conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 580)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
+        conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 580)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
+        conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 581)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
+        conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 581)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
+        conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 581)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
+        conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 581)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
+        conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 581)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
+        conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 581)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
+        conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 581)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
+        conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 615)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
+        conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 615)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
+        conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 615)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
+        conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 615)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
+        conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 615)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
+        conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 615)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
+        conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 615)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
+        conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 616)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
+        conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 616)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
+        conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 616)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
+        conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 616)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
+        conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 616)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
+        conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 616)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
+        conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 616)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
+        conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 617)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
+        conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 617)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
+        conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 617)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
+        conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 617)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
+        conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 617)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
+        conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 617)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
+        conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 617)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
+        conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 582)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
+        conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 582)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
+        conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 582)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
+        conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 582)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
+        conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 582)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
+        conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 582)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 72)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
+        conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 72)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 582)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
+        conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 583)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
+        conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 583)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
+        conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 583)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
+        conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 583)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
+        conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 583)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
+        conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 583)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 73)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
+        conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 73)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 583)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
+        conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 584)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
+        conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 584)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
+        conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 584)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
+        conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 584)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
+        conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 584)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
+        conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 584)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 74)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
+        conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 74)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 584)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
+        conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 618)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
+        conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 618)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
+        conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 618)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
+        conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 618)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
+        conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 618)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
+        conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 618)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 72)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
+        conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 72)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 618)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
+        conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 619)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
+        conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 619)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
+        conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 619)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
+        conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 619)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
+        conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 619)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
+        conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 619)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 73)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
+        conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 73)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 619)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
+        conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 620)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
+        conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 620)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
+        conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 620)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
+        conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 620)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
+        conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 620)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
+        conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 620)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 74)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
+        conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 74)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 620)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
+        conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 585)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
+        conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 585)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
+        conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 585)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
+        conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 585)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
+        conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 585)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
+        conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 585)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
+        conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 585)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
+        conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 586)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
+        conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 586)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
+        conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 586)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
+        conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 586)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
+        conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 586)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
+        conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 586)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
+        conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 586)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
+        conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 587)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
+        conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 587)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
+        conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 587)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
+        conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 587)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
+        conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 587)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
+        conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 587)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
+        conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 587)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
+        conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 621)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
+        conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 621)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
+        conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 621)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
+        conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 621)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
+        conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 621)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
+        conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 621)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
+        conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 621)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
+        conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 622)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
+        conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 622)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
+        conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 622)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
+        conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 622)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
+        conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 622)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
+        conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 622)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
+        conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 622)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
+        conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 623)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
+        conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 623)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
+        conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 623)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
+        conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 623)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
+        conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 623)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
+        conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 623)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
+        conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 623)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
+        conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 588)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
+        conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 588)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
+        conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 588)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
+        conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 588)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
+        conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 588)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
+        conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 588)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
+        conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 588)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
+        conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 589)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
+        conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 589)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
+        conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 589)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
+        conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 589)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
+        conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 589)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
+        conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 589)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
+        conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 589)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
+        conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 590)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
+        conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 590)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
+        conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 590)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
+        conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 590)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
+        conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 590)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
+        conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 590)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
+        conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 590)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
+        conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 624)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
+        conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 624)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
+        conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 624)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
+        conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 624)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
+        conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 624)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
+        conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 624)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
+        conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 624)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
+        conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 625)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
+        conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 625)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
+        conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 625)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
+        conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 625)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
+        conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 625)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
+        conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 625)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
+        conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 625)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
+        conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 626)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
+        conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 626)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
+        conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 626)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
+        conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 626)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
+        conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 626)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
+        conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 626)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
+        conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 626)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
+        conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 591)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
+        conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 591)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
+        conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 591)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
+        conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 591)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
+        conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 591)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
+        conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 591)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
+        conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 591)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
+        conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 592)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
+        conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 592)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
+        conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 592)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
+        conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 592)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
+        conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 592)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
+        conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 592)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 154)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
+        conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 154)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 592)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
+        conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 593)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
+        conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 593)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
+        conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 593)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
+        conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 593)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
+        conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 593)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
+        conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 593)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 155)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
+        conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 155)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 593)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
+        conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 627)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
+        conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 627)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
+        conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 627)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
+        conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 627)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
+        conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 627)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
+        conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 627)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
+        conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 627)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
+        conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 628)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
+        conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 628)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
+        conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 628)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
+        conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 628)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
+        conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 628)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
+        conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 628)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 154)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
+        conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 154)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 628)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
+        conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 629)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
+        conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 629)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
+        conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 629)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
+        conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 629)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
+        conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 629)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
+        conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 629)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 155)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
+        conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 155)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 629)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 162)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
+        conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 162)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 594)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 171)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
+        conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 171)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 594)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
+        conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 594)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
+        conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 594)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
+        conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 594)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
+        conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 594)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
+        conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 594)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 163)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
+        conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 163)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 595)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
+        conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 595)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
+        conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 595)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
+        conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 595)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
+        conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 595)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
+        conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 595)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
+        conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 595)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
+        conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 596)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
+        conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 596)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
+        conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 596)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
+        conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 596)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
+        conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 596)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
+        conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 596)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
+        conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 596)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 162)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
+        conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 162)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 630)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 171)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
+        conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 171)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 630)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
+        conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 630)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
+        conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 630)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
+        conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 630)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
+        conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 630)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
+        conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 630)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 163)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
+        conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 163)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 631)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
+        conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 631)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
+        conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 631)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
+        conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 631)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
+        conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 631)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
+        conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 631)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
+        conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 631)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
+        conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 632)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
+        conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 632)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
+        conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 632)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
+        conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 632)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
+        conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 632)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
+        conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 632)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
+        conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 632)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 171)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
+        conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 171)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 597)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
+        conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 597)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
+        conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 597)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
+        conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 597)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
+        conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 597)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
+        conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 597)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 225)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
+        conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 225)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 597)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
+        conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 598)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
+        conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 598)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
+        conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 598)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
+        conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 598)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
+        conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 598)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
+        conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 598)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 226)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
+        conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 226)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 598)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
+        conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 599)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
+        conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 599)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
+        conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 599)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
+        conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 599)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
+        conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 599)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
+        conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 599)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 227)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
+        conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 227)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 599)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 171)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
+        conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 171)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 633)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
+        conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 633)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
+        conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 633)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
+        conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 633)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
+        conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 633)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
+        conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 633)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 225)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
+        conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 225)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 633)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
+        conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 634)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
+        conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 634)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
+        conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 634)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
+        conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 634)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
+        conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 634)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
+        conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 634)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 226)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
+        conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 226)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 634)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
+        conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 635)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
+        conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 635)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
+        conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 635)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
+        conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 635)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
+        conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 635)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
+        conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 635)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 227)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
+        conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 227)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 635)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
+        conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 600)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
+        conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 600)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
+        conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 600)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
+        conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 600)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
+        conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 600)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 225)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
+        conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 225)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 600)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 234)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
+        conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 234)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 600)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
+        conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 601)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
+        conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 601)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
+        conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 601)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
+        conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 601)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
+        conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 601)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 226)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
+        conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 226)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 601)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 235)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
+        conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 235)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 601)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
+        conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 602)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
+        conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 602)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
+        conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 602)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
+        conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 602)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
+        conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 602)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 227)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
+        conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 227)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 602)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 236)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
+        conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 236)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 602)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
+        conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 636)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
+        conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 636)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
+        conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 636)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
+        conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 636)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
+        conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 636)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 225)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
+        conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 225)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 636)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 234)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
+        conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 234)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 636)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
+        conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 637)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
+        conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 637)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
+        conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 637)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
+        conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 637)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
+        conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 637)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 226)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
+        conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 226)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 637)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 235)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
+        conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 235)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 637)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
+        conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 638)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
+        conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 638)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
+        conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 638)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
+        conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 638)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
+        conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 638)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 227)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
+        conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 227)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 638)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 236)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
+        conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 236)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 638)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 243)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
+        conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 243)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 603)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
+        conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 603)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
+        conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 603)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
+        conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 603)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
+        conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 603)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
+        conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 603)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
+        conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 603)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 244)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
+        conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 244)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 604)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
+        conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 604)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
+        conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 604)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
+        conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 604)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
+        conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 604)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
+        conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 604)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
+        conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 604)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
+        conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 605)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
+        conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 605)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
+        conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 605)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
+        conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 605)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
+        conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 605)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
+        conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 605)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
+        conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 605)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 243)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
+        conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 243)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 639)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
+        conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 639)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
+        conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 639)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
+        conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 639)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
+        conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 639)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
+        conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 639)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
+        conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 639)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 244)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
+        conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 244)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 640)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
+        conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 640)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
+        conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 640)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
+        conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 640)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
+        conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 640)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
+        conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 640)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
+        conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 640)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
+        conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 641)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
+        conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 641)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
+        conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 641)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
+        conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 641)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
+        conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 641)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
+        conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 641)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
+        conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 641)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
+        conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 606)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
+        conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 606)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
+        conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 606)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
+        conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 606)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
+        conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 606)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
+        conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 606)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 306)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
+        conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 306)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 606)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
+        conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 607)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
+        conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 607)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
+        conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 607)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
+        conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 607)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
+        conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 607)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
+        conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 607)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 307)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
+        conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 307)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 607)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
+        conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 608)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
+        conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 608)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
+        conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 608)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
+        conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 608)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
+        conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 608)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
+        conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 608)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 308)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
+        conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 308)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 608)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
+        conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 642)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
+        conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 642)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
+        conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 642)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
+        conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 642)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
+        conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 642)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
+        conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 642)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 306)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
+        conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 306)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 642)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
+        conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 643)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
+        conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 643)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
+        conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 643)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
+        conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 643)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
+        conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 643)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
+        conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 643)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 307)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
+        conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 307)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 643)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
+        conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 644)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
+        conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 644)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
+        conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 644)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
+        conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 644)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
+        conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 644)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
+        conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 644)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 308)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
+        conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 308)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 644)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
+        conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 609)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
+        conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 609)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
+        conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 609)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
+        conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 609)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
+        conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 609)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 306)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
+        conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 306)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 609)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 315)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
+        conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 315)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 609)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
+        conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 610)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
+        conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 610)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
+        conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 610)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
+        conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 610)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
+        conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 610)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 307)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
+        conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 307)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 610)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
+        conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 610)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
+        conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 611)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
+        conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 611)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
+        conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 611)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
+        conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 611)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
+        conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 611)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 308)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
+        conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 308)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 611)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
+        conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 611)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
+        conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 645)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
+        conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 645)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
+        conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 645)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
+        conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 645)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
+        conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 645)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 306)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
+        conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 306)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 645)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 315)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
+        conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 315)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 645)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
+        conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 646)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
+        conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 646)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
+        conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 646)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
+        conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 646)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
+        conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 646)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 307)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
+        conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 307)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 646)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
+        conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 646)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
+        conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 647)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
+        conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 647)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
+        conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 647)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
+        conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 647)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
+        conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 647)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 308)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
+        conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 308)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 647)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
+        conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 647)]));
       }
       for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
         for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
-          compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[((i1_inner * 7) + i2_inner)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+          compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[((i1_inner * 7) + i2_inner)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+          compute[((((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7)) + 784)] = max((conv2d_nchw[(((i1_inner * 7) + i2_inner) + 14)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner) + 16)]), 0.000000e+00f);
         }
       }
     }
@@ -659,7 +2670,7 @@ In the example below we resume the status and do more 5 trials.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 3 minutes  15.021 seconds)
+   **Total running time of the script:** ( 3 minutes  22.385 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 50ce17428..101688d5e 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -647,7 +647,7 @@ so we can read the log file and load the best schedules.
     Evaluate inference time cost...
     Execution time summary:
      mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)  
-       9.8413       9.8386       9.8801       9.8052       0.0306   
+       9.7300       9.7563       9.7570       9.6767       0.0377   
                
 
 
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 9041058e2..7e8b5d6c7 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)  
-      757.2458     757.1720     757.5069     757.0584      0.1904   
+      762.7657     762.5522     763.3508     762.3940      0.4188   
                
 
 
@@ -694,7 +694,7 @@ Other Tips
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  21.767 seconds)
+   **Total running time of the script:** ( 1 minutes  23.952 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 0f0e6809f..2ee052440 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
@@ -397,76 +397,30 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
                  placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
                  compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
       buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
-      preflattened_buffer_map = {placeholder_6: placeholder_15: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_5: placeholder_18: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], [])} {
-      for (i0.outer.i1.outer.fused: int32, 0, 32) "parallel" {
-        allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global {
-          for (nb_j.inner: int32, 0, 2) {
-            for (i.inner.init: int32, 0, 64) {
-              let cse_var_1: int32 = ((i.inner.init*32) + (nb_j.inner*16))
-               {
-                compute_5: Buffer(compute_4, float32, [2048], [])[cse_var_1] = 0f32
-                compute_5[(cse_var_1 + 1)] = 0f32
-                compute_5[(cse_var_1 + 2)] = 0f32
-                compute_5[(cse_var_1 + 3)] = 0f32
-                compute_5[(cse_var_1 + 4)] = 0f32
-                compute_5[(cse_var_1 + 5)] = 0f32
-                compute_5[(cse_var_1 + 6)] = 0f32
-                compute_5[(cse_var_1 + 7)] = 0f32
-                compute_5[(cse_var_1 + 8)] = 0f32
-                compute_5[(cse_var_1 + 9)] = 0f32
-                compute_5[(cse_var_1 + 10)] = 0f32
-                compute_5[(cse_var_1 + 11)] = 0f32
-                compute_5[(cse_var_1 + 12)] = 0f32
-                compute_5[(cse_var_1 + 13)] = 0f32
-                compute_5[(cse_var_1 + 14)] = 0f32
-                compute_5[(cse_var_1 + 15)] = 0f32
+      preflattened_buffer_map = {placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_5: placeholder_18: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], [])} {
+      for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
+        allocate(compute_4: Pointer(global float32), float32, [512]), storage_scope = global {
+          for (i.outer.inner: int32, 0, 4) {
+            for (i.inner.init: int32, 0, 8) {
+              for (j.init: int32, 0, 16) {
+                compute_5: Buffer(compute_4, float32, [512], [])[(((i.outer.inner*128) + (i.inner.init*16)) + j.init)] = 0f32
               }
             }
-            for (elem_idx: int32, 0, let cse_var_2: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
-              for (i.inner: int32, 0, 64) {
-                let cse_var_21: int32 = (elem_idx*16)
-                let cse_var_20: int32 = ((i.inner*32) + (nb_j.inner*16))
-                let cse_var_19: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
-                let cse_var_18: int32 = ((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i.inner*256))
-                let cse_var_17: int32 = (cse_var_20 + 9)
-                let cse_var_16: int32 = (cse_var_20 + 8)
-                let cse_var_15: int32 = (cse_var_20 + 7)
-                let cse_var_14: int32 = (cse_var_20 + 6)
-                let cse_var_13: int32 = (cse_var_20 + 5)
-                let cse_var_12: int32 = (cse_var_20 + 4)
-                let cse_var_11: int32 = (cse_var_20 + 3)
-                let cse_var_10: int32 = (cse_var_20 + 2)
-                let cse_var_9: int32 = (cse_var_20 + 15)
-                let cse_var_8: int32 = (cse_var_20 + 14)
-                let cse_var_7: int32 = (cse_var_20 + 13)
-                let cse_var_6: int32 = (cse_var_20 + 12)
-                let cse_var_5: int32 = (cse_var_20 + 11)
-                let cse_var_4: int32 = (cse_var_20 + 10)
-                let cse_var_3: int32 = (cse_var_20 + 1)
-                 {
-                  compute_5[cse_var_20] = (compute_5[cse_var_20] + (placeholder_1[((placeholder_3[cse_var_19]*16) + cse_var_21)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
-                  compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
-                  compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
-                  compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
-                  compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
-                  compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
-                  compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
-                  compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
-                  compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
-                  compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
-                  compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
-                  compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
-                  compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
-                  compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
-                  compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
-                  compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+            for (elem_idx: int32, 0, let cse_var_1: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+              for (i.inner: int32, 0, 8) {
+                for (j: int32, 0, 16) {
+                  let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32)
+                  if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+                    let cse_var_3: int32 = (((i.outer.inner*128) + (i.inner*16)) + j)
+                    compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + j)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+                  }
                 }
               }
             }
           }
-          for (i0.inner: int32, 0, 64) {
-            let cse_var_22: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
-            compute[ramp(cse_var_22, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
+          for (i0.inner: int32, 0, 32) {
+            let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
+            compute[ramp(cse_var_4, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_4, 1, 16)]), broadcast(0f32, 16))
           }
         }
       }
@@ -522,7 +476,7 @@ We build the binary and check its correctness and performance.
 
  .. code-block:: none
 
-    Execution time of this operator: 1.845 ms
+    Execution time of this operator: 1.553 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 831402a3b..7e5fbca18 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
@@ -5,14 +5,14 @@
 
 Computation times
 =================
-**00:45.953** total execution time for **how_to_tune_with_autotvm** files:
+**00:46.289** 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``)           | 00:45.917 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)           | 00:46.254 | 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_x86.py` (``tune_relay_x86.py``)               | 00:00.019 | 0.0 MB |
 +--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``)             | 00:00.005 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``)             | 00:00.006 | 0.0 MB |
 +--------------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``)               | 00:00.005 | 0.0 MB |
 +--------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
index 4cbea0167..aec617821 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
@@ -1156,8 +1156,8 @@ for this template
     TimeoutError
 
             [('tile_f', [-1, 2, 1, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4909501
-    No: 9   GFLOPS: 216.81/216.81   result: MeasureResult(costs=(0.001067741427586207,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.152261257171631, timestamp=1661498480.8726752)        [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
-    No: 10  GFLOPS: 0.00/216.81     result: Traceback (most recent call last):
+    No: 9   GFLOPS: 192.94/192.94   result: MeasureResult(costs=(0.0011998708666666666,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.105665683746338, timestamp=1661510163.694395)        [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
+    No: 10  GFLOPS: 0.00/192.94     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1280,8 +1280,8 @@ for this template
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
     tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 4, 4, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5092711
-    No: 11  GFLOPS: 259.30/259.30   result: MeasureResult(costs=(0.0008928053204419888,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6899151802062988, timestamp=1661498481.7430823)      [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
-    No: 12  GFLOPS: 0.00/259.30     result: Traceback (most recent call last):
+    No: 11  GFLOPS: 261.08/261.08   result: MeasureResult(costs=(0.0008867000828729282,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4912402629852295, timestamp=1661510164.6044521)      [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
+    No: 12  GFLOPS: 0.00/261.08     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1404,7 +1404,7 @@ for this template
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
     tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 128, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,183542
-    No: 13  GFLOPS: 0.00/259.30     result: Traceback (most recent call last):
+    No: 13  GFLOPS: 0.00/261.08     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1527,7 +1527,7 @@ for this template
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
     tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 4, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2482196
-    No: 14  GFLOPS: 0.00/259.30     result: Traceback (most recent call last):
+    No: 14  GFLOPS: 0.00/261.08     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1650,9 +1650,9 @@ for this template
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
     tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 64, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10306226
-    No: 15  GFLOPS: 5.38/259.30     result: MeasureResult(costs=(0.04303303925,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8491942882537842, timestamp=1661498486.278752)       [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
-    No: 16  GFLOPS: 3.34/259.30     result: MeasureResult(costs=(0.06941368025,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.516972303390503, timestamp=1661498487.5165503)       [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
-    No: 17  GFLOPS: 0.00/259.30     result: Traceback (most recent call last):
+    No: 15  GFLOPS: 5.46/261.08     result: MeasureResult(costs=(0.04238295375,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8740129470825195, timestamp=1661510169.2188017)      [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
+    No: 16  GFLOPS: 3.36/261.08     result: MeasureResult(costs=(0.06898508675,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.61911940574646, timestamp=1661510170.4581182)        [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
+    No: 17  GFLOPS: 0.00/261.08     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
@@ -1670,8 +1670,8 @@ for this template
     TimeoutError
 
             [('tile_f', [-1, 2, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10195251
-    No: 18  GFLOPS: 27.91/259.30    result: MeasureResult(costs=(0.008294080785714286,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3092622756958008, timestamp=1661498498.5817828)       [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
-    No: 19  GFLOPS: 0.00/259.30     result: Traceback (most recent call last):
+    No: 18  GFLOPS: 26.09/261.08    result: MeasureResult(costs=(0.008873694833333333,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.168952465057373, timestamp=1661510181.3898182)        [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
+    No: 19  GFLOPS: 0.00/261.08     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1794,7 +1794,7 @@ for this template
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
     tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6956993
-    No: 20  GFLOPS: 0.00/259.30     result: Traceback (most recent call last):
+    No: 20  GFLOPS: 0.00/261.08     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1973,7 +1973,7 @@ and measure running time.
     Best config:
     [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
     Finish loading 20 records
-    Time cost of this operator: 0.001262
+    Time cost of this operator: 0.001254
 
 
 
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 411d38aef..59280911f 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
@@ -329,10 +329,10 @@ Timing the untuned program
     ########## Build without Autotuning ##########
     Node Name                                     Ops                                           Time(us)  Time(%)  Shape              Inputs  Outputs  Measurements(us)  
     ---------                                     ---                                           --------  -------  -----              ------  -------  ----------------  
-    tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  310.8     98.736   (1, 2, 10, 10, 3)  2       1        [310.8]           
-    tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       3.015     0.958    (1, 6, 10, 10)     1       1        [3.015]           
-    tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.964     0.306    (1, 1, 10, 10, 3)  1       1        [0.964]           
-    Total_time                                    -                                             314.779   -        -                  -       -        -                 
+    tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  308.9     98.728   (1, 2, 10, 10, 3)  2       1        [308.9]           
+    tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       3.017     0.964    (1, 6, 10, 10)     1       1        [3.017]           
+    tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.962     0.307    (1, 1, 10, 10, 3)  1       1        [0.962]           
+    Total_time                                    -                                             312.879   -        -                  -       -        -                 
 
 
 
@@ -398,10 +398,10 @@ Timing the tuned program
     ########## Build with Autotuning ##########
     Node Name                                     Ops                                           Time(us)  Time(%)  Shape              Inputs  Outputs  Measurements(us)  
     ---------                                     ---                                           --------  -------  -----              ------  -------  ----------------  
-    tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  132.7     97.987   (1, 6, 10, 10, 1)  2       1        [132.7]           
-    tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       1.767     1.305    (1, 6, 10, 10)     1       1        [1.767]           
-    tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.96      0.709    (1, 1, 10, 10, 3)  1       1        [0.96]            
-    Total_time                                    -                                             135.426   -        -                  -       -        -                 
+    tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  193.0     98.646   (1, 6, 10, 10, 1)  2       1        [193.0]           
+    tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       1.808     0.924    (1, 6, 10, 10)     1       1        [1.808]           
+    tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.841     0.43     (1, 3, 10, 10, 1)  1       1        [0.841]           
+    Total_time                                    -                                             195.649   -        -                  -       -        -                 
 
 
 
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 bf50018e3..a76b027e5 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
@@ -225,7 +225,7 @@ take about **2 minutes** to download the Stanford Cars, while COCO 2017 validati
  .. code-block:: none
 
 
-    '/tmp/tmpgxo_i92h/images/random'
+    '/tmp/tmpx4ylsxc9/images/random'
 
 
 
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
 
  .. code-block:: none
 
-    /tmp/tmpgxo_i92h/images/target contains 8144 images
-    /tmp/tmpgxo_i92h/images/random contains 5000 images
+    /tmp/tmpx4ylsxc9/images/target contains 8144 images
+    /tmp/tmpx4ylsxc9/images/random contains 5000 images
 
 
 
@@ -501,13 +501,13 @@ the time on our validation set).
  .. code-block:: none
 
     Epoch 1/3
-    328/328 - 56s - loss: 0.2188 - accuracy: 0.9243 - val_loss: 0.1368 - val_accuracy: 0.9615
+    328/328 - 56s - loss: 0.2243 - accuracy: 0.9248 - val_loss: 0.1480 - val_accuracy: 0.9554
     Epoch 2/3
-    328/328 - 52s - loss: 0.1021 - accuracy: 0.9624 - val_loss: 0.1230 - val_accuracy: 0.9588
+    328/328 - 53s - loss: 0.0924 - accuracy: 0.9653 - val_loss: 0.1522 - val_accuracy: 0.9596
     Epoch 3/3
-    328/328 - 52s - loss: 0.0689 - accuracy: 0.9749 - val_loss: 0.1342 - val_accuracy: 0.9581
+    328/328 - 52s - loss: 0.0627 - accuracy: 0.9766 - val_loss: 0.1156 - val_accuracy: 0.9668
 
-    <keras.callbacks.History object at 0x7f1b6c658410>
+    <keras.callbacks.History object at 0x7fa0ea0be690>
 
 
 
@@ -864,7 +864,7 @@ Arduino tutorial for how to do that `on GitHub <https://github.com/guberti/tvm-a
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 4 minutes  33.393 seconds)
+   **Total running time of the script:** ( 4 minutes  52.170 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 54b4c3e4f..ec8739edf 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
@@ -5,16 +5,16 @@
 
 Computation times
 =================
-**05:25.875** total execution time for **how_to_work_with_microtvm** files:
+**05:47.774** total execution time for **how_to_work_with_microtvm** files:
 
 +---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``)               | 04:33.393 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``)               | 04:52.170 | 0.0 MB |
 +---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)         | 00:41.659 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)         | 00:43.741 | 0.0 MB |
 +---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``)                   | 00:07.582 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``)                   | 00:08.399 | 0.0 MB |
 +---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)             | 00:03.238 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)             | 00:03.462 | 0.0 MB |
 +---------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``)             | 00:00.001 | 0.0 MB |
 +---------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index 512e050d0..7bc541520 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
 =================
-**00:42.133** total execution time for **how_to_work_with_relay** files:
+**00:40.403** 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``) | 00:30.851 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:32.535 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)           | 00:09.860 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)           | 00:06.285 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)                             | 00:01.415 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)                             | 00:01.576 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``)                 | 00:00.007 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
index ab185015d..c8cc78e69 100644
--- a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
@@ -261,7 +261,7 @@ The following example customizes CUDA lowering rule for :code:`exp`.
  .. code-block:: none
 
 
-    <function my_cuda_math_rule at 0x7f1af0aaae60>
+    <function my_cuda_math_rule at 0x7fa0d3eeb7a0>
 
 
 
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 d77772db0..643b63f6d 100644
--- a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
@@ -5,20 +5,20 @@
 
 Computation times
 =================
-**00:04.102** total execution time for **how_to_work_with_schedules** files:
+**00:04.433** total execution time for **how_to_work_with_schedules** files:
 
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)                 | 00:01.891 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)                 | 00:02.042 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)                     | 00:00.985 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)                     | 00:01.084 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)                     | 00:00.529 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)                     | 00:00.564 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)                               | 00:00.515 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)                               | 00:00.555 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)                     | 00:00.100 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)                     | 00:00.102 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.041 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.044 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)                               | 00:00.027 | 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 2b4814887..1b040c899 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -347,7 +347,7 @@ The importing needs to happen before the tensorized GEMV being executed.
                  C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
       buffer_map = {A_1: A, B_1: B, C_1: C}
       preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
-      attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp_y9hpy4f/input0.cc'\nsource_filename = \"/tmp/tmp_y9hpy4f/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/tmp3amilt2v/input0.cc'\nsource_filename = \"/tmp/tmp3amilt2v/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 ba1368741..41fce5efd 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
 =================
-**00:20.789** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:21.939** total execution time for **topic_vta_tutorials_autotvm** files:
 
 +---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:20.782 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:21.933 | 0.0 MB |
 +---------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``)     | 00:00.007 | 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 788943993..de555987b 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -291,7 +291,7 @@ The compilation steps are:
       DeprecationWarning,
     /workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the  new recommended usage.
       relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
-    resnet18_v1 inference graph built in 22.40s!
+    resnet18_v1 inference graph built in 23.92s!
 
 
 
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 5ae955ff1..ae94a44da 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -335,7 +335,7 @@ The compilation steps are:
       "target_host parameter is going to be deprecated. "
     /workspace/python/tvm/relay/build_module.py: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 15.75s!
+    yolov3-tiny inference graph built in 16.48s!
 
 
 
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 501cd441e..8d2a25758 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
 =================
-**01:30.257** total execution time for **topic_vta_tutorials_frontend** files:
+**01:33.604** total execution time for **topic_vta_tutorials_frontend** files:
 
 +------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)           | 00:47.782 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)           | 00:49.173 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:42.475 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:44.430 | 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 c96d4daa7..dbdbf038e 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
 =================
-**00:03.232** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.326** total execution time for **topic_vta_tutorials_optimize** files:
 
 +--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)         | 00:02.832 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)         | 00:02.896 | 0.0 MB |
 +--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.400 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.430 | 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 6b2c5b7fd..b363210e8 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
 =================
-**00:00.714** total execution time for **topic_vta_tutorials** files:
+**00:00.799** total execution time for **topic_vta_tutorials** files:
 
 +---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.378 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.427 | 0.0 MB |
 +---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.336 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.372 | 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 675da88b9..0fd6cc11c 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -326,7 +326,7 @@ We build the binary and check its correctness and performance.
 
  .. code-block:: none
 
-    Execution time of this operator: 93.813 ms
+    Execution time of this operator: 93.210 ms
 
 
 
@@ -442,6 +442,11 @@ Expression (TE) language that demonstrates how TVM can optimize computational
 operations.
 
 
+.. rst-class:: sphx-glr-timing
+
+   **Total running time of the script:** ( 1 minutes  4.143 seconds)
+
+
 .. _sphx_glr_download_tutorial_auto_scheduler_matmul_x86.py:
 
 .. only:: html
diff --git a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
index 6d8698a41..2863c3fe0 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -462,16 +462,16 @@ reduce variance, we take 5 measurements and average them.
     waiting for device...
     device available
     Get devices for measurement successfully!
-    No: 1   GFLOPS: 9.78/9.78       result: MeasureResult(costs=(0.027451259,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5723624229431152, timestamp=1661497299.3036754)        [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
-    No: 2   GFLOPS: 2.41/9.78       result: MeasureResult(costs=(0.11146283539999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9103398323059082, timestamp=1661497301.2377052)        [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
-    No: 3   GFLOPS: 11.92/11.92     result: MeasureResult(costs=(0.0225246556,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5563087463378906, timestamp=1661497302.2882857)       [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
-    No: 4   GFLOPS: 1.86/11.92      result: MeasureResult(costs=(0.14409954419999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.429912567138672, timestamp=1661497305.2848365) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
-    No: 5   GFLOPS: 3.71/11.92      result: MeasureResult(costs=(0.0723765506,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2980091571807861, timestamp=1661497307.2286367)       [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
-    No: 6   GFLOPS: 1.81/11.92      result: MeasureResult(costs=(0.14834068279999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5339272022247314, timestamp=1661497309.8070521)        [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
-    No: 7   GFLOPS: 0.81/11.92      result: MeasureResult(costs=(0.3324582232,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.440662622451782, timestamp=1661497315.2940075)        [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
-    No: 8   GFLOPS: 10.22/11.92     result: MeasureResult(costs=(0.026261416400000005,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5608134269714355, timestamp=1661497315.8758852)       [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
-    No: 9   GFLOPS: 1.72/11.92      result: MeasureResult(costs=(0.1563330036,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.601516008377075, timestamp=1661497318.5963092)        [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
-    No: 10  GFLOPS: 2.44/11.92      result: MeasureResult(costs=(0.10994736899999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8628089427947998, timestamp=1661497320.5162773)        [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+    No: 1   GFLOPS: 9.58/9.58       result: MeasureResult(costs=(0.028022104200000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5833556652069092, timestamp=1661508888.1242018)       [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+    No: 2   GFLOPS: 2.58/9.58       result: MeasureResult(costs=(0.10400062239999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.815676212310791, timestamp=1661508889.9530501) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+    No: 3   GFLOPS: 11.73/11.73     result: MeasureResult(costs=(0.022891103599999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5622000694274902, timestamp=1661508891.0384483)       [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+    No: 4   GFLOPS: 1.65/11.73      result: MeasureResult(costs=(0.16289647000000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.728848695755005, timestamp=1661508894.3621128) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+    No: 5   GFLOPS: 3.56/11.73      result: MeasureResult(costs=(0.0754774778,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3485438823699951, timestamp=1661508895.8383842)       [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+    No: 6   GFLOPS: 1.67/11.73      result: MeasureResult(costs=(0.16045670500000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7338662147521973, timestamp=1661508898.6112063)        [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+    No: 7   GFLOPS: 0.79/11.73      result: MeasureResult(costs=(0.33865831859999995,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.541009902954102, timestamp=1661508904.747499)  [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+    No: 8   GFLOPS: 10.11/11.73     result: MeasureResult(costs=(0.026555558,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5734848976135254, timestamp=1661508905.3373668)        [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+    No: 9   GFLOPS: 1.55/11.73      result: MeasureResult(costs=(0.1729799392,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.869478940963745, timestamp=1661508908.3270593)        [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+    No: 10  GFLOPS: 2.23/11.73      result: MeasureResult(costs=(0.120348228,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0347964763641357, timestamp=1661508910.4198854)        [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
 
 
 
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 21451f1f4..f261fbe25 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -327,7 +327,7 @@ standard deviation.
 
  .. code-block:: none
 
-    {'mean': 493.54259615000956, 'median': 493.3891927500099, 'std': 1.4214002487701203}
+    {'mean': 496.82912881002267, 'median': 497.1657699500156, 'std': 0.7228006462395927}
 
 
 
@@ -563,30 +563,30 @@ the tuning data to.
 
     /workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-
    [Task  1/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  1/25]  Current/Best:   17.55/  17.55 GFLOPS | Progress: (4/20) | 6.39 s
    [Task  1/25]  Current/Best:    6.15/  17.55 GFLOPS | Progress: (8/20) | 9.41 s
    [Task  1/25]  Current/Best:   11.54/  22.78 GFLOPS | Progress: (12/20) | 11.86 s
    [Task  1/25]  Current/Best:   16.47/  22.78 GFLOPS | Progress: (16/20) | 13.54 s
    [Task  1/25]  Current/Best:   11.59/  23.89 GFLOPS | Progress: (20/20) | 15.27 s Done.
-
    [Task  2/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  2/25]  Current/Best:   12.33/  13.22 GFLOPS | Progress: (4/20) | 3.91 s
    [Task  2/25]  Current/Best:   14.24/  18.64 GFLOPS | Progress: (8/20) | 5.21 s
    [Task  2/25]  Current/Best:   21.34/  21.34 GFLOPS | Progress: (12/20) | 6.54 s
    [Task  2/25]  Current/Best:   12.09/  21.34 GFLOPS | Progress: (16/20) | 7.83 s
    [Task  2/25]  Current/Best:   19.61/  21.34 GFLOPS | Progress: (20/20) | 9.45 s Done.
-
    [Task  3/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  3/25]  Current/Best:    1.63/  10.84 GFLOPS | Progress: (4/20) | 5.85 s
    [Task  3/25]  Current/Best:   15.36/  16.83 GFLOPS | Progress: (8/20) | 7.76 s
    [Task  3/25]  Current/Best:   15.01/  16.83 GFLOPS | Progress: (12/20) | 9.47 s
    [Task  3/25]  Current/Best:    7.20/  23.74 GFLOPS | Progress: (16/20) | 11.37 s
    [Task  3/25]  Current/Best:   11.48/  23.74 GFLOPS | Progress: (20/20) | 15.96 s Done.
-
    [Task  4/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  4/25]  Current/Best:    9.48/  20.44 GFLOPS | Progress: (4/20) | 2.39 s
    [Task  4/25]  Current/Best:    6.57/  20.44 GFLOPS | Progress: (8/20) | 7.13 s
    [Task  4/25]  Current/Best:   22.52/  22.52 GFLOPS | Progress: (12/20) | 12.00 s
    [Task  4/25]  Current/Best:   16.23/  22.52 GFLOPS | Progress: (16/20) | 14.43 s
    [Task  4/25]  Current/Best:   13.49/  22.52 GFLOPS | Progress: (20/20) | 16.51 s Done.
-
    [Task  5/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  5/25]  Current/Best:    9.78/  10.46 GFLOPS | Progress: (4/20) | 2.60 s
    [Task  5/25]  Current/Best:   11.87/  12.87 GFLOPS | Progress: (8/20) | 4.65 s
    [Task  5/25]  Current/Best:   11.58/  18.04 GFLOPS | Progress: (12/20) | 7.73 s
    [Task  5/25]  Current/Best:   12.03/  22.34 GFLOPS | Progress: (16/20) | 9.16 s
    [Task  5/25]  Current/Best:   12.03/  22.34 GFLOPS | Progress: (20/20) | 11.07 s Done.
-
    [Task  6/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  6/25]  Current/Best:   12.17/  20.08 GFLOPS | Progress: (4/20) | 4.13 s
    [Task  6/25]  Current/Best:   19.01/  20.08 GFLOPS | Progress: (8/20) | 5.90 s
    [Task  6/25]  Current/Best:   13.31/  20.08 GFLOPS | Progress: (12/20) | 7.83 s
    [Task  6/25]  Current/Best:   20.08/  20.08 GFLOPS | Progress: (16/20) | 10.08 s
    [Task  6/25]  Current/Best:    3.74/  20.08 GFLOPS | Progress: (20/20) | 12.59 s Done.
-
    [Task  7/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  7/25]  Current/Best:   11.14/  12.89 GFLOPS | Progress: (4/20) | 3.57 s
    [Task  7/25]  Current/Best:   19.86/  21.09 GFLOPS | Progress: (8/20) | 5.10 s
    [Task  7/25]  Current/Best:   15.92/  21.09 GFLOPS | Progress: (12/20) | 6.99 s
    [Task  7/25]  Current/Best:   12.20/  21.09 GFLOPS | Progress: (16/20) | 9.01 s
    [Task  7/25]  Current/Best:    6.45/  21.71 GFLOPS | Progress: (20/20) | 11.46 s Done.
-
    [Task  8/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  8/25]  Current/Best:   10.11/  13.90 GFLOPS | Progress: (4/20) | 2.93 s
    [Task  8/25]  Current/Best:    9.60/  13.90 GFLOPS | Progress: (8/20) | 8.07 s
    [Task  8/25]  Current/Best:   13.58/  13.90 GFLOPS | Progress: (12/20) | 14.46 s
    [Task  8/25]  Current/Best:   18.94/  18.94 GFLOPS | Progress: (16/20) | 16.55 s
    [Task  8/25]  Current/Best:   19.76/  19.76 GFLOPS | Progress: (20/20) | 23.62 s Done.
-
    [Task  9/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  9/25]  Current/Best:   14.36/  15.70 GFLOPS | Progress: (4/20) | 11.94 s
    [Task  9/25]  Current/Best:   23.09/  23.09 GFLOPS | Progress: (8/20) | 13.72 s
    [Task  9/25]  Current/Best:    8.28/  23.09 GFLOPS | Progress: (12/20) | 16.25 s
    [Task  9/25]  Current/Best:   17.90/  23.09 GFLOPS | Progress: (16/20) | 19.04 s
    [Task  9/25]  Current/Best:    9.22/  23.09 GFLOPS | Progress: (20/20) | 27.62 s
    [Task 10/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 10/25]  Current/Best:   18.34/  18.34 GFLOPS | Progress: (4/20) | 2.57 s
    [Task 10/25]  Current/Best:   15.63/  18.34 GFLOPS | Progress: (8/20) | 4.22 s
    [Task 10/25]  Current/Best:   12.80/  18.95 GFLOPS | Progress: (12/20) | 5.76 s
    [Task 10/25]  Current/Best:   19.16/  20.45 GFLOPS | Progress: (16/20) | 6.86 s
    [Task 10/25]  Current/Best:    8.90/  20.45 GFLOPS | Progress: (20/20
 ) | 8.37 s Done.
-
    [Task 11/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 11/25]  Current/Best:   12.31/  18.23 GFLOPS | Progress: (4/20) | 3.33 s
    [Task 11/25]  Current/Best:   17.02/  18.23 GFLOPS | Progress: (8/20) | 6.13 s
    [Task 11/25]  Current/Best:   18.05/  18.23 GFLOPS | Progress: (12/20) | 8.18 s
    [Task 11/25]  Current/Best:   13.54/  20.98 GFLOPS | Progress: (16/20) | 11.11 s
    [Task 11/25]  Current/Best:   19.51/  21.36 GFLOPS | Progress: (20/20) | 13.22 s Done.
-
    [Task 12/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 12/25]  Current/Best:    7.74/  18.04 GFLOPS | Progress: (4/20) | 5.78 s
    [Task 12/25]  Current/Best:    5.31/  18.04 GFLOPS | Progress: (8/20) | 9.70 s
    [Task 12/25]  Current/Best:   18.75/  18.80 GFLOPS | Progress: (12/20) | 11.69 s
    [Task 12/25]  Current/Best:   15.29/  18.80 GFLOPS | Progress: (16/20) | 14.64 s
    [Task 12/25]  Current/Best:   15.12/  18.80 GFLOPS | Progress: (20/20) | 16.55 s Done.
-
    [Task 13/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 13/25]  Current/Best:    8.61/  17.36 GFLOPS | Progress: (4/20) | 3.77 s
    [Task 13/25]  Current/Best:   15.86/  20.94 GFLOPS | Progress: (8/20) | 6.38 s
    [Task 13/25]  Current/Best:   19.68/  21.65 GFLOPS | Progress: (12/20) | 9.37 s
    [Task 13/25]  Current/Best:   12.33/  21.65 GFLOPS | Progress: (16/20) | 12.80 s
    [Task 13/25]  Current/Best:   18.44/  21.65 GFLOPS | Progress: (20/20) | 15.20 s Done.
-
    [Task 14/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 14/25]  Current/Best:   13.86/  13.86 GFLOPS | Progress: (4/20) | 3.40 s
    [Task 14/25]  Current/Best:    6.12/  13.86 GFLOPS | Progress: (8/20) | 5.61 s
    [Task 14/25]  Current/Best:   20.37/  20.37 GFLOPS | Progress: (12/20) | 8.27 s
    [Task 14/25]  Current/Best:   17.59/  20.37 GFLOPS | Progress: (16/20) | 9.93 s Done.
-
    [Task 14/25]  Current/Best:   17.07/  20.37 GFLOPS | Progress: (20/20) | 11.68 s
    [Task 15/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 15/25]  Current/Best:   16.19/  17.61 GFLOPS | Progress: (4/20) | 2.71 s
    [Task 15/25]  Current/Best:   14.34/  18.09 GFLOPS | Progress: (8/20) | 4.01 s
    [Task 15/25]  Current/Best:   10.41/  22.26 GFLOPS | Progress: (12/20) | 6.26 s
    [Task 15/25]  Current/Best:   20.23/  22.26 GFLOPS | Progress: (16/20) | 9.31 s
    [Task 15/25]  Current/Best:    9.67/  22.26 GFLOPS | Progress: (20/20) | 10.32 s
    [Task 16/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 16/25]  Current/Best:   20.80/  20.80 GFLOPS | Progress: (4/20) | 3.00 s
    [Task 16/25]  Current/Best:    3.02/  20.80 GFLOPS | Progress: (8/20) | 4.61 s
    [Task 16/25]  Current/Best:   19.40/  20.80 GFLOPS | Progress: (12/20) | 5.82 s
    [Task 16/25]  Current/Best:   18.18/  20.80 GFLOPS | Progress: (16/20) |
  7.21 s
    [Task 16/25]  Current/Best:   10.08/  22.18 GFLOPS | Progress: (20/20) | 9.36 s Done.
-
    [Task 17/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 17/25]  Current/Best:   12.97/  18.49 GFLOPS | Progress: (4/20) | 4.78 s
    [Task 17/25]  Current/Best:   12.95/  23.42 GFLOPS | Progress: (8/20) | 7.69 s
    [Task 17/25]  Current/Best:   17.84/  23.42 GFLOPS | Progress: (12/20) | 9.73 s
    [Task 17/25]  Current/Best:   16.46/  23.42 GFLOPS | Progress: (16/20) | 11.98 s
    [Task 17/25]  Current/Best:   10.06/  23.42 GFLOPS | Progress: (20/20) | 14.14 s Done.
-
    [Task 18/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 18/25]  Current/Best:   11.25/  18.04 GFLOPS | Progress: (4/20) | 3.82 s
    [Task 18/25]  Current/Best:   10.58/  19.64 GFLOPS | Progress: (8/20) | 7.49 s
    [Task 18/25]  Current/Best:   19.33/  19.64 GFLOPS | Progress: (12/20) | 9.42 s
    [Task 18/25]  Current/Best:   10.07/  19.64 GFLOPS | Progress: (16/20) | 13.26 s
    [Task 18/25]  Current/Best:   20.69/  20.69 GFLOPS | Progress: (20/20) | 14.77 s Done.
-
    [Task 19/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 19/25]  Current/Best:    7.29/  20.54 GFLOPS | Progress: (4/20) | 6.00 s
    [Task 19/25]  Current/Best:    2.69/  20.54 GFLOPS | Progress: (8/20) | 9.34 s
    [Task 19/25]  Current/Best:   20.09/  21.54 GFLOPS | Progress: (12/20) | 12.28 s
    [Task 19/25]  Current/Best:   13.68/  21.74 GFLOPS | Progress: (16/20) | 15.37 s
    [Task 19/25]  Current/Best:    2.70/  23.16 GFLOPS | Progress: (20/20) | 18.17 s Done.
-
    [Task 20/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 20/25]  Current/Best:    8.68/  15.24 GFLOPS | Progress: (4/20) | 3.35 s Done.
+
    [Task  1/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  1/25]  Current/Best:   17.49/  17.49 GFLOPS | Progress: (4/20) | 6.97 s
    [Task  1/25]  Current/Best:    6.16/  17.49 GFLOPS | Progress: (8/20) | 9.48 s
    [Task  1/25]  Current/Best:   11.49/  22.71 GFLOPS | Progress: (12/20) | 11.97 s
    [Task  1/25]  Current/Best:   16.46/  22.77 GFLOPS | Progress: (16/20) | 13.67 s
    [Task  1/25]  Current/Best:   11.55/  23.88 GFLOPS | Progress: (20/20) | 15.46 s Done.
+
    [Task  2/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  2/25]  Current/Best:   12.20/  12.98 GFLOPS | Progress: (4/20) | 3.86 s
    [Task  2/25]  Current/Best:   13.67/  18.05 GFLOPS | Progress: (8/20) | 5.16 s
    [Task  2/25]  Current/Best:   20.98/  20.98 GFLOPS | Progress: (12/20) | 6.49 s
    [Task  2/25]  Current/Best:   12.48/  20.98 GFLOPS | Progress: (16/20) | 7.76 s
    [Task  2/25]  Current/Best:   20.15/  20.98 GFLOPS | Progress: (20/20) | 9.37 s Done.
+
    [Task  3/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  3/25]  Current/Best:    1.63/  10.82 GFLOPS | Progress: (4/20) | 5.90 s
    [Task  3/25]  Current/Best:   15.26/  16.78 GFLOPS | Progress: (8/20) | 7.83 s
    [Task  3/25]  Current/Best:   14.96/  16.78 GFLOPS | Progress: (12/20) | 9.54 s
    [Task  3/25]  Current/Best:    7.20/  23.60 GFLOPS | Progress: (16/20) | 11.49 s
    [Task  3/25]  Current/Best:   11.85/  23.60 GFLOPS | Progress: (20/20) | 16.07 s Done.
+
    [Task  4/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  4/25]  Current/Best:    9.55/  20.01 GFLOPS | Progress: (4/20) | 2.43 s
    [Task  4/25]  Current/Best:    6.70/  20.01 GFLOPS | Progress: (8/20) | 7.23 s
    [Task  4/25]  Current/Best:   20.94/  20.94 GFLOPS | Progress: (12/20) | 12.33 s
    [Task  4/25]  Current/Best:   16.14/  20.94 GFLOPS | Progress: (16/20) | 14.78 s
    [Task  4/25]  Current/Best:   13.25/  20.94 GFLOPS | Progress: (20/20) | 16.90 s Done.
+
    [Task  5/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  5/25]  Current/Best:    9.57/  10.20 GFLOPS | Progress: (4/20) | 2.64 s
    [Task  5/25]  Current/Best:   11.62/  13.15 GFLOPS | Progress: (8/20) | 4.72 s
    [Task  5/25]  Current/Best:   11.09/  18.03 GFLOPS | Progress: (12/20) | 7.93 s
    [Task  5/25]  Current/Best:   11.60/  22.71 GFLOPS | Progress: (16/20) | 9.36 s
    [Task  5/25]  Current/Best:   11.73/  22.71 GFLOPS | Progress: (20/20) | 11.30 s Done.
+
    [Task  6/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  6/25]  Current/Best:   12.04/  19.95 GFLOPS | Progress: (4/20) | 4.20 s
    [Task  6/25]  Current/Best:   18.92/  19.95 GFLOPS | Progress: (8/20) | 5.99 s
    [Task  6/25]  Current/Best:   12.88/  19.95 GFLOPS | Progress: (12/20) | 7.96 s
    [Task  6/25]  Current/Best:   20.00/  20.00 GFLOPS | Progress: (16/20) | 10.21 s
    [Task  6/25]  Current/Best:    3.69/  20.00 GFLOPS | Progress: (20/20) | 12.73 s Done.
+
    [Task  7/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  7/25]  Current/Best:   10.96/  12.62 GFLOPS | Progress: (4/20) | 3.69 s
    [Task  7/25]  Current/Best:   20.07/  21.02 GFLOPS | Progress: (8/20) | 5.22 s
    [Task  7/25]  Current/Best:   16.16/  21.02 GFLOPS | Progress: (12/20) | 7.18 s
    [Task  7/25]  Current/Best:   12.15/  21.02 GFLOPS | Progress: (16/20) | 9.23 s
    [Task  7/25]  Current/Best:    6.40/  21.68 GFLOPS | Progress: (20/20) | 11.70 s Done.
+
    [Task  8/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  8/25]  Current/Best:    9.75/  14.39 GFLOPS | Progress: (4/20) | 2.98 s
    [Task  8/25]  Current/Best:    9.30/  14.39 GFLOPS | Progress: (8/20) | 8.25 s
    [Task  8/25]  Current/Best:   13.27/  14.39 GFLOPS | Progress: (12/20) | 14.83 s
    [Task  8/25]  Current/Best:   18.77/  18.77 GFLOPS | Progress: (16/20) | 16.96 s
    [Task  8/25]  Current/Best:   19.75/  19.75 GFLOPS | Progress: (20/20) | 24.23 s Done.
+
    [Task  9/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  9/25]  Current/Best:   14.24/  15.81 GFLOPS | Progress: (4/20) | 12.01 s
    [Task  9/25]  Current/Best:   22.94/  22.94 GFLOPS | Progress: (8/20) | 13.82 s
    [Task  9/25]  Current/Best:    8.27/  22.94 GFLOPS | Progress: (12/20) | 16.37 s
    [Task  9/25]  Current/Best:   17.95/  22.94 GFLOPS | Progress: (16/20) | 19.29 s
    [Task  9/25]  Current/Best:    9.05/  22.94 GFLOPS | Progress: (20/20) | 27.96 s
    [Task 10/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 10/25]  Current/Best:   18.21/  18.21 GFLOPS | Progress: (4/20) | 2.65 s
    [Task 10/25]  Current/Best:   15.78/  18.21 GFLOPS | Progress: (8/20) | 4.30 s
    [Task 10/25]  Current/Best:   12.31/  18.96 GFLOPS | Progress: (12/20) | 5.88 s
    [Task 10/25]  Current/Best:   19.16/  20.38 GFLOPS | Progress: (16/20) | 7.00 s
    [Task 10/25]  Current/Best:    8.91/  20.38 GFLOPS | Progress: (20/20
 ) | 8.55 s Done.
+
    [Task 11/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 11/25]  Current/Best:   12.22/  18.01 GFLOPS | Progress: (4/20) | 3.47 s
    [Task 11/25]  Current/Best:   16.91/  18.01 GFLOPS | Progress: (8/20) | 6.33 s
    [Task 11/25]  Current/Best:   18.05/  18.05 GFLOPS | Progress: (12/20) | 8.45 s
    [Task 11/25]  Current/Best:   13.09/  20.80 GFLOPS | Progress: (16/20) | 11.43 s
    [Task 11/25]  Current/Best:   19.44/  21.54 GFLOPS | Progress: (20/20) | 13.57 s Done.
+
    [Task 12/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 12/25]  Current/Best:    7.77/  18.17 GFLOPS | Progress: (4/20) | 5.81 s
    [Task 12/25]  Current/Best:    5.20/  18.17 GFLOPS | Progress: (8/20) | 9.79 s
    [Task 12/25]  Current/Best:   18.83/  18.83 GFLOPS | Progress: (12/20) | 11.78 s
    [Task 12/25]  Current/Best:   14.84/  18.83 GFLOPS | Progress: (16/20) | 14.78 s
    [Task 12/25]  Current/Best:   15.11/  18.83 GFLOPS | Progress: (20/20) | 16.72 s Done.
+
    [Task 13/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 13/25]  Current/Best:    8.65/  17.37 GFLOPS | Progress: (4/20) | 3.82 s
    [Task 13/25]  Current/Best:   15.48/  20.83 GFLOPS | Progress: (8/20) | 6.49 s
    [Task 13/25]  Current/Best:   19.43/  21.84 GFLOPS | Progress: (12/20) | 9.53 s
    [Task 13/25]  Current/Best:   12.22/  21.84 GFLOPS | Progress: (16/20) | 13.03 s
    [Task 13/25]  Current/Best:   18.23/  21.84 GFLOPS | Progress: (20/20) | 15.43 s Done.
+
    [Task 14/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 14/25]  Current/Best:   13.78/  13.78 GFLOPS | Progress: (4/20) | 3.47 s
    [Task 14/25]  Current/Best:    6.08/  13.78 GFLOPS | Progress: (8/20) | 5.68 s
    [Task 14/25]  Current/Best:   20.40/  20.40 GFLOPS | Progress: (12/20) | 8.40 s
    [Task 14/25]  Current/Best:   16.52/  20.40 GFLOPS | Progress: (16/20) | 10.11 s Done.
+
    [Task 14/25]  Current/Best:   17.05/  20.40 GFLOPS | Progress: (20/20) | 11.88 s
    [Task 15/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 15/25]  Current/Best:   16.20/  17.59 GFLOPS | Progress: (4/20) | 2.77 s
    [Task 15/25]  Current/Best:   14.49/  18.03 GFLOPS | Progress: (8/20) | 4.07 s
    [Task 15/25]  Current/Best:   10.34/  21.99 GFLOPS | Progress: (12/20) | 6.37 s
    [Task 15/25]  Current/Best:   20.39/  21.99 GFLOPS | Progress: (16/20) | 10.16 s
    [Task 15/25]  Current/Best:    9.65/  21.99 GFLOPS | Progress: (20/20) | 11.19 s
    [Task 16/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 16/25]  Current/Best:   20.07/  20.07 GFLOPS | Progress: (4/20) | 3.13 s
    [Task 16/25]  Current/Best:    3.04/  20.07 GFLOPS | Progress: (8/20) | 4.75 s
    [Task 16/25]  Current/Best:   19.15/  20.07 GFLOPS | Progress: (12/20) | 5.97 s
    [Task 16/25]  Current/Best:   17.92/  20.07 GFLOPS | Progress: (16/20) 
 | 7.35 s
    [Task 16/25]  Current/Best:   10.02/  21.87 GFLOPS | Progress: (20/20) | 9.55 s Done.
+
    [Task 17/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 17/25]  Current/Best:   13.07/  18.37 GFLOPS | Progress: (4/20) | 4.91 s
    [Task 17/25]  Current/Best:   13.29/  23.17 GFLOPS | Progress: (8/20) | 7.72 s
    [Task 17/25]  Current/Best:   16.94/  23.17 GFLOPS | Progress: (12/20) | 9.81 s
    [Task 17/25]  Current/Best:   16.35/  23.17 GFLOPS | Progress: (16/20) | 12.05 s
    [Task 17/25]  Current/Best:   10.03/  23.17 GFLOPS | Progress: (20/20) | 14.24 s Done.
+
    [Task 18/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 18/25]  Current/Best:   11.54/  18.06 GFLOPS | Progress: (4/20) | 3.86 s
    [Task 18/25]  Current/Best:   10.51/  19.21 GFLOPS | Progress: (8/20) | 7.61 s
    [Task 18/25]  Current/Best:   19.57/  19.57 GFLOPS | Progress: (12/20) | 9.54 s
    [Task 18/25]  Current/Best:   10.10/  19.57 GFLOPS | Progress: (16/20) | 13.49 s
    [Task 18/25]  Current/Best:   20.68/  20.68 GFLOPS | Progress: (20/20) | 15.01 s Done.
+
    [Task 19/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 19/25]  Current/Best:    7.08/  20.20 GFLOPS | Progress: (4/20) | 6.24 s
    [Task 19/25]  Current/Best:    2.69/  20.20 GFLOPS | Progress: (8/20) | 9.53 s
    [Task 19/25]  Current/Best:   19.94/  21.61 GFLOPS | Progress: (12/20) | 12.50 s
    [Task 19/25]  Current/Best:   13.65/  21.91 GFLOPS | Progress: (16/20) | 15.54 s
    [Task 19/25]  Current/Best:    2.70/  23.07 GFLOPS | Progress: (20/20) | 18.30 s Done.
+
    [Task 20/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 20/25]  Current/Best:   10.18/  15.68 GFLOPS | Progress: (4/20) | 3.37 s Done.
      Done.
-
    [Task 20/25]  Current/Best:    9.64/  15.24 GFLOPS | Progress: (8/20) | 6.87 s
    [Task 20/25]  Current/Best:    2.31/  16.50 GFLOPS | Progress: (12/20) | 10.80 s
    [Task 20/25]  Current/Best:   12.30/  16.50 GFLOPS | Progress: (16/20) | 14.66 s
    [Task 20/25]  Current/Best:   11.63/  22.27 GFLOPS | Progress: (20/20) | 16.78 s
    [Task 21/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 21/25]  Current/Best:    6.40/  17.66 GFLOPS | Progress: (4/20) | 3.29 s
    [Task 21/25]  Current/Best:   14.63/  17.66 GFLOPS | Progress: (8/20) | 4.93 s
    [Task 21/25]  Current/Best:    1.61/  17.66 GFLOPS | Progress: (12/20) | 7.06 s
    [Task 21/25]  Current/Best:   16.07/  17.66 GFLOPS | Progress: (16/20) | 10.57 s
    [Task 21/25]  Current/Best:    4.47/  17.66 GFLOPS | Progress: (20/20) | 17.78 s
    [Task 22/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 22/25]  Current/Best:    2.71/  17.01 GFLOPS | Progress: (4/20
 ) | 2.68 s
    [Task 22/25]  Current/Best:    8.67/  22.06 GFLOPS | Progress: (8/20) | 4.66 s
    [Task 22/25]  Current/Best:   20.00/  22.06 GFLOPS | Progress: (12/20) | 7.05 s
    [Task 22/25]  Current/Best:   15.78/  22.06 GFLOPS | Progress: (16/20) | 9.20 s
    [Task 22/25]  Current/Best:   13.90/  22.06 GFLOPS | Progress: (20/20) | 10.93 s Done.
-
    [Task 23/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 23/25]  Current/Best:   17.70/  20.96 GFLOPS | Progress: (4/20) | 3.28 s
    [Task 23/25]  Current/Best:   14.65/  20.96 GFLOPS | Progress: (8/20) | 6.64 s
    [Task 23/25]  Current/Best:   20.98/  21.54 GFLOPS | Progress: (12/20) | 8.48 s
    [Task 23/25]  Current/Best:    6.40/  21.54 GFLOPS | Progress: (16/20) | 15.55 s
    [Task 23/25]  Current/Best:    8.00/  21.54 GFLOPS | Progress: (20/20) | 19.73 s Done.
-
    [Task 24/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 24/25]  Current/Best:    7.90/   7.90 GFLOPS | Progress: (4/20) | 11.80 s
    [Task 24/25]  Current/Best:    3.53/   7.90 GFLOPS | Progress: (8/20) | 23.03 s
    [Task 24/25]  Current/Best:    4.36/   7.90 GFLOPS | Progress: (12/20) | 33.75 s Done.
-
    [Task 24/25]  Current/Best:    7.21/   8.60 GFLOPS | Progress: (16/20) | 39.40 s
    [Task 24/25]  Current/Best:    3.31/   8.86 GFLOPS | Progress: (20/20) | 45.35 s Done.
-
    [Task 25/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 25/25]  Current/Best:    1.55/   2.77 GFLOPS | Progress: (4/20) | 11.62 s
    [Task 25/25]  Current/Best:    6.17/   8.50 GFLOPS | Progress: (8/20) | 22.92 s
    [Task 25/25]  Current/Best:    6.05/   8.50 GFLOPS | Progress: (12/20) | 34.33 s
    [Task 25/25]  Current/Best:    5.88/   8.77 GFLOPS | Progress: (16/20) | 36.08 s
    [Task 25/25]  Current/Best:    2.82/   8.96 GFLOPS | Progress: (20/20) | 46.79 s
+
    [Task 20/25]  Current/Best:   10.60/  15.68 GFLOPS | Progress: (8/20) | 6.94 s
    [Task 20/25]  Current/Best:    2.32/  15.75 GFLOPS | Progress: (12/20) | 10.93 s
    [Task 20/25]  Current/Best:   12.58/  15.75 GFLOPS | Progress: (16/20) | 14.91 s
    [Task 20/25]  Current/Best:   12.74/  22.17 GFLOPS | Progress: (20/20) | 17.03 s
    [Task 21/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 21/25]  Current/Best:    6.40/  17.67 GFLOPS | Progress: (4/20) | 3.33 s
    [Task 21/25]  Current/Best:   14.62/  17.67 GFLOPS | Progress: (8/20) | 4.93 s
    [Task 21/25]  Current/Best:    1.61/  17.67 GFLOPS | Progress: (12/20) | 7.09 s
    [Task 21/25]  Current/Best:   18.12/  18.12 GFLOPS | Progress: (16/20) | 10.65 s
    [Task 21/25]  Current/Best:    4.32/  18.12 GFLOPS | Progress: (20/20) | 18.04 s
    [Task 22/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 22/25]  Current/Best:    2.70/  16.97 GFLOPS | Progress: (4/20
 ) | 2.71 s
    [Task 22/25]  Current/Best:    8.55/  21.99 GFLOPS | Progress: (8/20) | 4.76 s
    [Task 22/25]  Current/Best:   19.99/  21.99 GFLOPS | Progress: (12/20) | 7.16 s
    [Task 22/25]  Current/Best:   15.51/  21.99 GFLOPS | Progress: (16/20) | 9.30 s
    [Task 22/25]  Current/Best:   14.19/  21.99 GFLOPS | Progress: (20/20) | 10.98 s Done.
+
    [Task 23/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 23/25]  Current/Best:   17.41/  20.61 GFLOPS | Progress: (4/20) | 3.28 s
    [Task 23/25]  Current/Best:   16.12/  20.61 GFLOPS | Progress: (8/20) | 6.68 s
    [Task 23/25]  Current/Best:   20.95/  21.29 GFLOPS | Progress: (12/20) | 8.54 s
    [Task 23/25]  Current/Best:    6.29/  21.29 GFLOPS | Progress: (16/20) | 15.79 s
    [Task 23/25]  Current/Best:    7.65/  21.29 GFLOPS | Progress: (20/20) | 20.07 s Done.
+
    [Task 24/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 24/25]  Current/Best:    8.66/   8.66 GFLOPS | Progress: (4/20) | 11.82 s
    [Task 24/25]  Current/Best:    3.43/   8.66 GFLOPS | Progress: (8/20) | 23.13 s
    [Task 24/25]  Current/Best:    4.57/   8.66 GFLOPS | Progress: (12/20) | 33.87 s Done.
+
    [Task 24/25]  Current/Best:    6.29/   8.73 GFLOPS | Progress: (16/20) | 39.61 s
    [Task 24/25]  Current/Best:    3.35/   9.04 GFLOPS | Progress: (20/20) | 45.69 s Done.
+
    [Task 25/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 25/25]  Current/Best:    1.55/   2.84 GFLOPS | Progress: (4/20) | 11.63 s
    [Task 25/25]  Current/Best:    5.79/   7.84 GFLOPS | Progress: (8/20) | 22.91 s
    [Task 25/25]  Current/Best:    6.06/   7.84 GFLOPS | Progress: (12/20) | 34.33 s
    [Task 25/25]  Current/Best:    5.90/   8.65 GFLOPS | Progress: (16/20) | 36.15 s
    [Task 25/25]  Current/Best:    2.84/   8.97 GFLOPS | Progress: (20/20) | 46.84 s
 
 
 
@@ -748,8 +748,8 @@ improvement in comparing the optimized model to the unoptimized model.
 
  .. code-block:: none
 
-    optimized: {'mean': 403.32067872999687, 'median': 403.15202960000533, 'std': 0.7764659365570964}
-    unoptimized: {'mean': 493.54259615000956, 'median': 493.3891927500099, 'std': 1.4214002487701203}
+    optimized: {'mean': 416.0598285800097, 'median': 416.12317290000647, 'std': 0.42267072556587304}
+    unoptimized: {'mean': 496.82912881002267, 'median': 497.1657699500156, 'std': 0.7228006462395927}
 
 
 
@@ -772,7 +772,7 @@ profiling/benchmarking.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 10 minutes  20.798 seconds)
+   **Total running time of the script:** ( 10 minutes  32.959 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 b1222b7a5..4e9989b9e 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -282,7 +282,7 @@ device and returns the measured cost. Network overhead is excluded.
 
  .. code-block:: none
 
-    1.236e-07 secs/op
+    1.247e-07 secs/op
 
 
 
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 7ac4e1086..e776f4006 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -263,7 +263,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
 
  .. code-block:: none
 
-    [stage(a, placeholder(a, 0xcf9b870)), stage(b, placeholder(b, 0xf234080)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min= [...]
+    [stage(a, placeholder(a, 0x1fd440a0)), stage(b, placeholder(b, 0x1fe60240)), 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 5848ef61f..edbcbe56c 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
 =================
-**13:11.842** total execution time for **tutorial** files:
+**13:37.843** total execution time for **tutorial** files:
 
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)                 | 10:20.798 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)                 | 10:32.959 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)     | 00:58.590 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:04.143 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 00:55.629 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)     | 01:02.030 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)                 | 00:30.771 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)                 | 00:31.396 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)               | 00:24.688 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)               | 00:25.907 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)                               | 00:00.700 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)                               | 00:00.711 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)       | 00:00.511 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)       | 00:00.520 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.147 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.166 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``)                           | 00:00.005 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``)                           | 00:00.007 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_tutorial_uma.py` (``uma.py``)                                             | 00:00.001 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``)   | 00:00.001 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_install.py` (``install.py``)                                     | 00:00.001 | 0.0 MB |
-+------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``)                             | 00:00.001 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_tutorial_install.py` (``install.py``)                                     | 00:00.001 | 0.0 MB |
++------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index d7c797668..4a20e5d2a 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -301,7 +301,7 @@ helper function to run a profile of the TVM generated code.
 
  .. code-block:: none
 
-    Numpy running time: 0.000009
+    Numpy running time: 0.000007
     naive: 0.000006
 
 
@@ -512,10 +512,10 @@ We can now compare the different schedules
  .. code-block:: none
 
                 Operator                  Timing             Performance
-                   numpy    9.308509997936199e-06                    1.0
-                   naive              5.9669e-06      0.6410155869546178
-                parallel              6.0376e-06      0.6486107874771154
-                  vector    2.4614100000000002e-05    2.6442577819067954
+                   numpy    6.763130004401319e-06                    1.0
+                   naive              5.8218e-06      0.8608144448223354
+                parallel              6.0604e-06      0.8960939677421556
+                  vector             2.45745e-05       3.633598642049964
 
 
 
@@ -936,7 +936,7 @@ matrix multiplication.
 
  .. code-block:: none
 
-    Numpy running time: 0.018811
+    Numpy running time: 0.018810
 
 
 
@@ -996,7 +996,7 @@ optimizations.
 
     /workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-    none: 3.234482
+    none: 3.465276
 
 
 
@@ -1101,7 +1101,7 @@ schedule.
 
     /workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-    blocking: 0.302805
+    blocking: 0.329411
 
 
 
@@ -1199,7 +1199,7 @@ already cache friendly from our previous optimizations.
 
     /workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-    vectorization: 0.334609
+    vectorization: 0.348340
     @main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
       attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
       buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1275,7 +1275,7 @@ more cache friendly.
 
     /workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-    loop permutation: 0.114968
+    loop permutation: 0.116431
     @main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
       attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
       buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1376,7 +1376,7 @@ optimized schedule.
 
     /workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-    array packing: 0.108062
+    array packing: 0.107095
     @main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
       attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
       buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1471,7 +1471,7 @@ to `C` when all the block results are ready.
 
     /workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-    block caching: 0.110685
+    block caching: 0.109822
     @main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
       attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
       buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1559,7 +1559,7 @@ of thread-level parallelization.
 
     /workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-    parallelization: 0.145251
+    parallelization: 0.146118
     @main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
       attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
       buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1640,13 +1640,13 @@ working, we can compare the results.
  .. code-block:: none
 
                 Operator                  Timing             Performance
-                    none            3.2344822942                     1.0
-                blocking     0.30280530969999997      0.0936178597245635
-           vectorization     0.33460907619999997     0.10345058212252803
-        loop permutation     0.11496817200000001      0.0355445358925471
-           array packing     0.10806193370000002     0.03340934464033833
-           block caching            0.1106849964      0.0342203129689341
-         parallelization            0.1452510715     0.04490705413984207
+                    none            3.4652755868                     1.0
+                blocking     0.32941065680000003     0.09506045004177965
+           vectorization     0.34833980369999995     0.10052297284143957
+        loop permutation     0.11643082999999999    0.033599298838889104
+           array packing     0.10709526359999999    0.030905265949972206
+           block caching            0.1098222515    0.031692212855548116
+         parallelization            0.1461180403    0.042166354923283994
 
 
 
@@ -1686,6 +1686,11 @@ 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  2.030 seconds)
+
+
 .. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
 
 .. only:: html
diff --git a/docs/commit_hash b/docs/commit_hash
index c05ddebe5..e9b2560c7 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-3224817d0835909c2673184a6c20bac3b7672632
+4f431c87c2b8bb5ea0773c44d92658e506251dda
diff --git a/docs/genindex.html b/docs/genindex.html
index 7c733a8a6..52ff6cfbf 100644
--- a/docs/genindex.html
+++ b/docs/genindex.html
@@ -3082,8 +3082,6 @@
 </li>
       <li><a href="reference/api/python/ir.html#tvm.ir.PoolInfo">PoolInfo (class in tvm.ir)</a>
 </li>
-  </ul></td>
-  <td style="width: 33%; vertical-align: top;"><ul>
       <li><a href="reference/api/python/ir.html#tvm.ir.PoolInfoProperties">PoolInfoProperties (class in tvm.ir)</a>
 </li>
       <li><a href="reference/api/python/te.html#tvm.te.popcount">popcount() (in module tvm.te)</a>
@@ -3092,6 +3090,8 @@
         <li><a href="reference/api/python/tir.html#tvm.tir.popcount">(in module tvm.tir)</a>
 </li>
       </ul></li>
+  </ul></td>
+  <td style="width: 33%; vertical-align: top;"><ul>
       <li><a href="reference/api/python/rpc.html#tvm.rpc.PopenSession">PopenSession (class in tvm.rpc)</a>
 </li>
       <li><a href="reference/api/python/relay/analysis.html#tvm.relay.analysis.post_order_visit">post_order_visit() (in module tvm.relay.analysis)</a>
@@ -3163,6 +3163,14 @@
       <li><a href="reference/api/python/autotvm.html#tvm.autotvm.tuner.callback.progress_bar">progress_bar() (in module tvm.autotvm.tuner.callback)</a>
 </li>
       <li><a href="reference/api/python/relay/vision.html#tvm.relay.vision.proposal">proposal() (in module tvm.relay.vision)</a>
+</li>
+      <li><a href="reference/api/python/tir.html#tvm.tir.ptx_commit_group">ptx_commit_group() (in module tvm.tir)</a>
+</li>
+      <li><a href="reference/api/python/tir.html#tvm.tir.ptx_cp_async">ptx_cp_async() (in module tvm.tir)</a>
+</li>
+      <li><a href="reference/api/python/tir.html#tvm.tir.ptx_ldmatrix">ptx_ldmatrix() (in module tvm.tir)</a>
+</li>
+      <li><a href="reference/api/python/tir.html#tvm.tir.ptx_wait_group">ptx_wait_group() (in module tvm.tir)</a>
 </li>
   </ul></td>
 </tr></table>
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index 112619be1..03a47b0fb 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -574,6 +574,7 @@ 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  6.401 seconds)</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-darknet-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/7716f96385bd5abb6e822041e285be54/from_darknet.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_darknet.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 91912e415..4a291f476 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -427,7 +427,7 @@ to download the full example code</p>
 <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.zipa97be0da-0169-4616-8f5c-a2d16f3b792d 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.zip24111cca-40d1-49e3-a31c-1ffdd1f8de77 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 bdc0fd2c4..2d4f9b567 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -432,12 +432,12 @@ python3 -m pip install -f https://release.oneflow.info <span class="nv">oneflow<
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: &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, 59.9MB/s]
- 35%|###4      | 14.3M/41.5M [00:00&lt;00:00, 48.0MB/s]
- 46%|####6     | 19.1M/41.5M [00:00&lt;00:00, 45.9MB/s]
- 58%|#####7    | 24.0M/41.5M [00:00&lt;00:00, 46.4MB/s]
- 77%|#######7  | 32.1M/41.5M [00:00&lt;00:00, 53.4MB/s]
-100%|##########| 41.5M/41.5M [00:00&lt;00:00, 58.0MB/s]
+ 19%|#9        | 7.99M/41.5M [00:00&lt;00:00, 52.0MB/s]
+ 39%|###8      | 16.0M/41.5M [00:00&lt;00:00, 50.5MB/s]
+ 57%|#####7    | 23.8M/41.5M [00:00&lt;00:00, 60.9MB/s]
+ 72%|#######2  | 29.9M/41.5M [00:00&lt;00:00, 60.5MB/s]
+ 87%|########6 | 35.9M/41.5M [00:00&lt;00:00, 43.3MB/s]
+100%|##########| 41.5M/41.5M [00:00&lt;00:00, 50.2MB/s]
 </pre></div>
 </div>
 </div>
diff --git a/docs/how_to/compile_models/from_pytorch.html b/docs/how_to/compile_models/from_pytorch.html
index f582ab1e9..5046c9c5d 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -414,9 +414,9 @@ be unstable.</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>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]
- 37%|###6      | 16.4M/44.7M [00:00&lt;00:00, 172MB/s]
- 88%|########8 | 39.4M/44.7M [00:00&lt;00:00, 212MB/s]
-100%|##########| 44.7M/44.7M [00:00&lt;00:00, 212MB/s]
+ 38%|###7      | 16.8M/44.7M [00:00&lt;00:00, 176MB/s]
+ 82%|########1 | 36.4M/44.7M [00:00&lt;00:00, 194MB/s]
+100%|##########| 44.7M/44.7M [00:00&lt;00:00, 186MB/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 f3ff41998..a97dacff8 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -636,7 +636,7 @@ banana (score = 0.00022)
 desk (score = 0.00019)
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  1.023 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  4.461 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 ef0131750..ae71a7555 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -327,7 +327,7 @@
             
   <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>04:53.309</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:15.248</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 81%" />
@@ -335,44 +335,44 @@
 <col style="width: 8%" />
 </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>01:01.023</p></td>
+<tr class="row-odd"><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>01:06.401</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>00:59.281</p></td>
+<tr class="row-even"><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>01:04.461</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>00:38.293</p></td>
+<td><p>00:41.004</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="from_oneflow.html#sphx-glr-how-to-compile-models-from-oneflow-py"><span class="std std-ref">Compile OneFlow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_oneflow.py</span></code>)</p></td>
-<td><p>00:27.333</p></td>
+<td><p>00:29.429</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>00:24.496</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
+<td><p>00:26.212</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
-<tr class="row-even"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
-<td><p>00:24.217</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
+<td><p>00:25.790</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
-<td><p>00:21.478</p></td>
+<td><p>00:23.010</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></td>
-<td><p>00:19.442</p></td>
+<td><p>00:20.545</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>00:15.434</p></td>
+<td><p>00:15.918</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>00:02.310</p></td>
+<td><p>00:02.479</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 </tbody>
diff --git a/docs/how_to/deploy_models/deploy_model_on_android.html b/docs/how_to/deploy_models/deploy_model_on_android.html
index 4aa1466f3..9203e4097 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -653,7 +653,7 @@ to the remote android device.</p>
 Evaluate inference time cost...
 Execution time summary:
  mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)
-  16.3936      16.6600      16.9417      15.6985       0.4797
+  16.2030      16.2295      16.4214      15.9420       0.1322
 </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 8fb1f3521..a05ae73e0 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -436,15 +436,38 @@ be unstable.</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>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]
-  2%|2         | 3.47M/170M [00:00&lt;00:04, 36.1MB/s]
-  4%|4         | 7.09M/170M [00:00&lt;00:04, 37.2MB/s]
- 21%|##1       | 35.7M/170M [00:00&lt;00:00, 157MB/s]
- 33%|###3      | 56.5M/170M [00:00&lt;00:00, 181MB/s]
- 48%|####7     | 81.2M/170M [00:00&lt;00:00, 209MB/s]
- 62%|######2   | 106M/170M [00:00&lt;00:00, 225MB/s]
- 78%|#######7  | 132M/170M [00:00&lt;00:00, 243MB/s]
- 94%|#########3| 159M/170M [00:00&lt;00:00, 254MB/s]
-100%|##########| 170M/170M [00:00&lt;00:00, 210MB/s]
+  3%|3         | 5.67M/170M [00:00&lt;00:02, 59.4MB/s]
+  7%|6         | 11.3M/170M [00:00&lt;00:02, 58.7MB/s]
+ 10%|9         | 16.9M/170M [00:00&lt;00:03, 51.4MB/s]
+ 13%|#3        | 22.6M/170M [00:00&lt;00:02, 54.2MB/s]
+ 16%|#6        | 27.9M/170M [00:00&lt;00:02, 54.8MB/s]
+ 20%|#9        | 33.7M/170M [00:00&lt;00:02, 56.6MB/s]
+ 23%|##3       | 39.9M/170M [00:00&lt;00:02, 59.3MB/s]
+ 27%|##6       | 45.6M/170M [00:00&lt;00:02, 56.4MB/s]
+ 30%|###       | 51.0M/170M [00:01&lt;00:02, 47.4MB/s]
+ 34%|###3      | 57.0M/170M [00:01&lt;00:02, 51.3MB/s]
+ 37%|###6      | 62.5M/170M [00:01&lt;00:02, 52.9MB/s]
+ 40%|####      | 68.5M/170M [00:01&lt;00:01, 55.3MB/s]
+ 44%|####3     | 74.0M/170M [00:01&lt;00:01, 55.6MB/s]
+ 47%|####6     | 79.4M/170M [00:01&lt;00:01, 53.3MB/s]
+ 50%|####9     | 84.6M/170M [00:01&lt;00:01, 50.6MB/s]
+ 53%|#####3    | 90.2M/170M [00:01&lt;00:01, 53.1MB/s]
+ 56%|#####6    | 95.5M/170M [00:01&lt;00:01, 53.5MB/s]
+ 59%|#####9    | 101M/170M [00:01&lt;00:01, 53.6MB/s]
+ 63%|######2   | 107M/170M [00:02&lt;00:01, 56.2MB/s]
+ 66%|######5   | 112M/170M [00:02&lt;00:01, 56.4MB/s]
+ 69%|######9   | 118M/170M [00:02&lt;00:00, 58.1MB/s]
+ 73%|#######2  | 124M/170M [00:02&lt;00:00, 54.6MB/s]
+ 76%|#######5  | 129M/170M [00:02&lt;00:00, 55.0MB/s]
+ 79%|#######9  | 134M/170M [00:02&lt;00:00, 50.0MB/s]
+ 82%|########1 | 139M/170M [00:02&lt;00:00, 42.7MB/s]
+ 84%|########4 | 143M/170M [00:02&lt;00:00, 41.6MB/s]
+ 87%|########6 | 148M/170M [00:03&lt;00:00, 40.4MB/s]
+ 89%|########9 | 152M/170M [00:03&lt;00:00, 37.9MB/s]
+ 93%|#########2| 157M/170M [00:03&lt;00:00, 43.3MB/s]
+ 96%|#########5| 162M/170M [00:03&lt;00:00, 46.3MB/s]
+ 98%|#########8| 167M/170M [00:03&lt;00:00, 43.3MB/s]
+100%|##########| 170M/170M [00:03&lt;00:00, 49.6MB/s]
 /usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
   for i in range(dim)
 /usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the &#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=&#39;floor&#39;).
@@ -539,7 +562,7 @@ torchvision rcnn models.</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes  51.184 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  7.822 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 3249de88a..197f2ad90 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -480,7 +480,9 @@ training. Other models require a full post training calibration.</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: &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]
-100%|##########| 13.6M/13.6M [00:00&lt;00:00, 186MB/s]
+ 26%|##6       | 3.54M/13.6M [00:00&lt;00:00, 31.2MB/s]
+ 63%|######2   | 8.49M/13.6M [00:00&lt;00:00, 42.5MB/s]
+100%|##########| 13.6M/13.6M [00:00&lt;00:00, 58.6MB/s]
 </pre></div>
 </div>
 </div>
@@ -569,7 +571,7 @@ 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)
-  90.1168      90.0889      91.4455      89.8083       0.2969
+  90.4677      90.3767      94.2328      90.0733       0.5179
 </pre></div>
 </div>
 <div class="admonition note">
@@ -608,7 +610,7 @@ 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  7.102 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  11.881 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 0a276010e..cc5930fb3 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -573,7 +573,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
  mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)
-  119.6067     119.3060     146.4217     117.5544      2.7795
+  121.3751     121.3598     122.9928     120.4364      0.3941
 </pre></div>
 </div>
 <div class="admonition note">
@@ -601,7 +601,7 @@ 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  0.237 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes  1.613 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 be4f7c67c..d65ca5730 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -509,7 +509,7 @@ 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  15.268 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  43.351 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 21083c10e..a26a264cb 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -441,24 +441,24 @@ to your device.</p>
 Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
 
   0%|          | 0/132723 [00:00&lt;?, ?KB/s]
-  4%|4         | 5617/132723 [00:00&lt;00:02, 56166.71KB/s]
- 10%|#         | 13279/132723 [00:00&lt;00:01, 68192.35KB/s]
- 16%|#5        | 20877/132723 [00:00&lt;00:01, 71745.92KB/s]
- 21%|##1       | 28527/132723 [00:00&lt;00:01, 73619.45KB/s]
- 27%|##7       | 36242/132723 [00:00&lt;00:01, 74890.16KB/s]
- 33%|###3      | 43904/132723 [00:00&lt;00:01, 75474.81KB/s]
- 39%|###8      | 51553/132723 [00:00&lt;00:01, 75805.16KB/s]
- 45%|####4     | 59294/132723 [00:00&lt;00:00, 76311.77KB/s]
- 50%|#####     | 66993/132723 [00:00&lt;00:00, 76522.43KB/s]
- 56%|#####6    | 74717/132723 [00:01&lt;00:00, 76740.24KB/s]
- 62%|######2   | 82392/132723 [00:01&lt;00:00, 76545.10KB/s]
- 68%|######7   | 90061/132723 [00:01&lt;00:00, 76585.24KB/s]
- 74%|#######3  | 98083/132723 [00:01&lt;00:00, 77683.44KB/s]
- 80%|########  | 106591/132723 [00:01&lt;00:00, 79912.95KB/s]
- 87%|########6 | 115060/132723 [00:01&lt;00:00, 81350.55KB/s]
- 93%|#########3| 123490/132723 [00:01&lt;00:00, 82235.51KB/s]
- 99%|#########9| 131951/132723 [00:01&lt;00:00, 82943.63KB/s]
-100%|##########| 132723/132723 [00:01&lt;00:00, 77510.05KB/s]
+  4%|3         | 5015/132723 [00:00&lt;00:02, 50145.86KB/s]
+  9%|9         | 12478/132723 [00:00&lt;00:01, 64545.76KB/s]
+ 15%|#5        | 20057/132723 [00:00&lt;00:01, 69678.07KB/s]
+ 21%|##        | 27505/132723 [00:00&lt;00:01, 71570.54KB/s]
+ 26%|##6       | 35103/132723 [00:00&lt;00:01, 73159.43KB/s]
+ 32%|###2      | 42576/132723 [00:00&lt;00:01, 73691.34KB/s]
+ 38%|###7      | 50113/132723 [00:00&lt;00:01, 74238.16KB/s]
+ 43%|####3     | 57695/132723 [00:00&lt;00:01, 74738.45KB/s]
+ 49%|####9     | 65245/132723 [00:00&lt;00:00, 74975.47KB/s]
+ 55%|#####4    | 72791/132723 [00:01&lt;00:00, 75122.58KB/s]
+ 61%|######    | 80304/132723 [00:01&lt;00:00, 75057.07KB/s]
+ 66%|######6   | 87857/132723 [00:01&lt;00:00, 75194.98KB/s]
+ 72%|#######1  | 95515/132723 [00:01&lt;00:00, 75612.66KB/s]
+ 78%|#######7  | 103077/132723 [00:01&lt;00:00, 75276.44KB/s]
+ 83%|########3 | 110627/132723 [00:01&lt;00:00, 75341.67KB/s]
+ 89%|########9 | 118238/132723 [00:01&lt;00:00, 75571.06KB/s]
+ 95%|#########4| 125813/132723 [00:01&lt;00:00, 75621.12KB/s]
+100%|##########| 132723/132723 [00:01&lt;00:00, 73993.14KB/s]
 </pre></div>
 </div>
 <p>Create TVM runtime and do inference
@@ -501,7 +501,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
 <span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
 </pre></div>
 </div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes  35.161 seconds)</p>
+<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes  40.989 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 209788957..1ce0fce3b 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -327,7 +327,7 @@
             
   <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>11:02.842</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>12:02.548</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 86%" />
@@ -336,35 +336,35 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>02:51.184</p></td>
+<td><p>03:07.822</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>02:35.161</p></td>
+<td><p>02:40.989</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>02:00.237</p></td>
+<td><p>02:01.613</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>01:15.268</p></td>
+<td><p>01:43.351</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>01:07.102</p></td>
+<td><p>01:11.881</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:28.951</p></td>
+<td><p>00:30.443</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><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>00:22.704</p></td>
+<td><p>00:23.438</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><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>00:22.230</p></td>
+<td><p>00:23.004</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><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 6f93a14a5..504082c0f 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -612,7 +612,7 @@ 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.zip4f61c6d4-1303-47fa-a368-340a17a98374 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.zip6f76c4cb-29f9-46ef-a272-c0c11b644acf 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 1eaba1034..de1246229 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -327,7 +327,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:40.510</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:42.886</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 84%" />
@@ -336,19 +336,19 @@
 </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>00:37.382</p></td>
+<td><p>00:39.644</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>00:02.202</p></td>
+<td><p>00:02.279</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="use_pass_infra.html#sphx-glr-how-to-extend-tvm-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></td>
-<td><p>00:00.918</p></td>
+<td><p>00:00.956</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>00:00.009</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 bcbc19b09..25101207f 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -512,10 +512,10 @@ 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: 6778us [6778us] (46.27%; 46.27%)
-FoldScaleAxis: 7869us [6us] (53.73%; 53.73%)
-        FoldConstant: 7864us [1632us] (53.69%; 99.93%)
-                InferType: 6232us [6232us] (42.54%; 79.25%)
+InferType: 6794us [6794us] (46.09%; 46.09%)
+FoldScaleAxis: 7947us [5us] (53.91%; 53.91%)
+        FoldConstant: 7941us [1649us] (53.87%; 99.93%)
+                InferType: 6292us [6292us] (42.69%; 79.23%)
 </pre></div>
 </div>
 </div>
@@ -537,10 +537,10 @@ 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: 6256us [6256us] (44.66%; 44.66%)
-FoldScaleAxis: 7752us [5us] (55.34%; 55.34%)
-        FoldConstant: 7747us [1607us] (55.30%; 99.94%)
-                InferType: 6140us [6140us] (43.83%; 79.25%)
+InferType: 6344us [6344us] (43.25%; 43.25%)
+FoldScaleAxis: 8325us [4us] (56.75%; 56.75%)
+        FoldConstant: 8320us [1641us] (56.72%; 99.95%)
+                InferType: 6680us [6680us] (45.54%; 80.28%)
 </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 f54d6a9c5..17b0fdd4f 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -564,7 +564,7 @@ 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: 52.792715 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 48.048866 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 e2fa0b6ec..dc26a114c 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -906,7 +906,7 @@ 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: 9.696405 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 9.910798 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 4f7ece975..451178791 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -461,8 +461,8 @@ 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: 0.018475
-Baseline: 3.207243
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019208
+Baseline: 3.461791
 </pre></div>
 </div>
 <p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -522,7 +522,7 @@ 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: 0.310522
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.318913
 </pre></div>
 </div>
 <p>Here is the generated IR after blocking.</p>
@@ -589,7 +589,7 @@ 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: 0.344958
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.349989
 </pre></div>
 </div>
 <p>Here is the generated IR after vectorization.</p>
@@ -650,7 +650,7 @@ 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: 0.115670
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.121454
 </pre></div>
 </div>
 <p>Here is the generated IR after loop permutation.</p>
@@ -733,7 +733,7 @@ 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: 0.109684
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109826
 </pre></div>
 </div>
 <p>Here is the generated IR after array packing.</p>
@@ -819,7 +819,7 @@ 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: 0.110460
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.110997
 </pre></div>
 </div>
 <p>Here is the generated IR after blocking.</p>
@@ -909,7 +909,7 @@ 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: 0.146852
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.147262
 </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 7e572af3a..2b0c9048d 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -327,7 +327,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:34.120</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:35.432</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 83%" />
@@ -336,15 +336,15 @@
 </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>00:31.872</p></td>
+<td><p>00:32.965</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>00:01.237</p></td>
+<td><p>00:01.357</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>00:01.011</p></td>
+<td><p>00:01.110</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 f6ccc0212..09c8c5dec 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -327,7 +327,7 @@
             
   <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>05:59.708</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>06:11.482</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 85%" />
@@ -336,27 +336,27 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></td>
-<td><p>03:15.021</p></td>
+<td><p>03:22.385</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>01:21.767</p></td>
+<td><p>01:23.952</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="tune_network_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></td>
-<td><p>00:46.378</p></td>
+<td><p>00:47.473</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>00:19.391</p></td>
+<td><p>00:19.683</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></td>
-<td><p>00:08.706</p></td>
+<td><p>00:09.068</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></td>
-<td><p>00:08.447</p></td>
+<td><p>00:08.920</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 45ac53436..64eb43ce8 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
@@ -491,102 +491,1118 @@ cooperative fetching, unrolling and operator fusion.</p>
              compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
   buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
   preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
-  attr [IterVar(blockIdx.x: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;blockIdx.x&quot;)] &quot;thread_extent&quot; = 32;
-  allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
-  allocate(pad_temp.shared: Pointer(shared float32), float32, [162]), storage_scope = shared;
-  allocate(kernel.shared: Pointer(shared float32), float32, [288]), storage_scope = shared;
+  attr [IterVar(blockIdx.x: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;blockIdx.x&quot;)] &quot;thread_extent&quot; = 16;
+  allocate(conv2d_nchw: Pointer(local float32), float32, [28]), storage_scope = local;
+  allocate(pad_temp.shared: Pointer(shared float32), float32, [324]), storage_scope = shared;
+  allocate(kernel.shared: Pointer(shared float32), float32, [1152]), storage_scope = shared;
   attr [IterVar(threadIdx.x: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56 {
-    conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope=&quot;local&quot;, align=32)[0] = 0f32
+    conv2d_nchw_1: Buffer(conv2d_nchw, float32, [196], [], scope=&quot;local&quot;, align=32)[0] = 0f32
+    conv2d_nchw_1[14] = 0f32
     conv2d_nchw_1[1] = 0f32
+    conv2d_nchw_1[15] = 0f32
     conv2d_nchw_1[2] = 0f32
+    conv2d_nchw_1[16] = 0f32
     conv2d_nchw_1[3] = 0f32
+    conv2d_nchw_1[17] = 0f32
     conv2d_nchw_1[4] = 0f32
+    conv2d_nchw_1[18] = 0f32
     conv2d_nchw_1[5] = 0f32
+    conv2d_nchw_1[19] = 0f32
     conv2d_nchw_1[6] = 0f32
+    conv2d_nchw_1[20] = 0f32
     conv2d_nchw_1[7] = 0f32
+    conv2d_nchw_1[21] = 0f32
     conv2d_nchw_1[8] = 0f32
+    conv2d_nchw_1[22] = 0f32
     conv2d_nchw_1[9] = 0f32
+    conv2d_nchw_1[23] = 0f32
     conv2d_nchw_1[10] = 0f32
+    conv2d_nchw_1[24] = 0f32
     conv2d_nchw_1[11] = 0f32
+    conv2d_nchw_1[25] = 0f32
     conv2d_nchw_1[12] = 0f32
+    conv2d_nchw_1[26] = 0f32
     conv2d_nchw_1[13] = 0f32
-    for (rc.outer.outer: int32, 0, 256) {
-      let cse_var_2: int32 = (rc.outer.outer*98)
-      let cse_var_1: int32 = (rc.outer.outer*18)
+    conv2d_nchw_1[27] = 0f32
+    for (rc.outer.outer: int32, 0, 128) {
+      let cse_var_2: int32 = (rc.outer.outer*196)
+      let cse_var_1: int32 = (rc.outer.outer*36)
        {
         attr [IterVar(threadIdx.x_1: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
-        pad_temp.shared_1: Buffer(pad_temp.shared, float32, [162], [], scope=&quot;shared&quot;)[threadIdx.x_1] = @tir.if_then_else((((9 &lt;= threadIdx.x_1) &amp;&amp; (1 &lt;= floormod(threadIdx.x_1, 9))) &amp;&amp; (floormod(threadIdx.x_1, 9) &lt; 8)), data[(((cse_var_2 + (floordiv(threadIdx.x_1, 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+        pad_temp.shared_1: Buffer(pad_temp.shared, float32, [324], [], scope=&quot;shared&quot;)[threadIdx.x_1] = @tir.if_then_else((((9 &lt;= threadIdx.x_1) &amp;&amp; (1 &lt;= floormod(threadIdx.x_1, 9))) &amp;&amp; (floormod(threadIdx.x_1, 9) &lt; 8)), data[(((cse_var_2 + (floordiv(threadIdx.x_1, 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
         attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
         pad_temp.shared_1[(threadIdx.x_1 + 56)] = @tir.if_then_else(((((9 &lt;= floormod((threadIdx.x_1 + 56), 81)) &amp;&amp; (floormod((threadIdx.x_1 + 56), 81) &lt; 72)) &amp;&amp; (1 &lt;= floormod((threadIdx.x_1 + 2), 9))) &amp;&amp; (floormod((threadIdx.x_1 + 2), 9) &lt; 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 56), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 56), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
         attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
-        if @tir.likely((threadIdx.x_1 &lt; 50), dtype=bool) {
-          pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else((((threadIdx.x_1 &lt; 41) &amp;&amp; (1 &lt;= floormod((threadIdx.x_1 + 4), 9))) &amp;&amp; (floormod((threadIdx.x_1 + 4), 9) &lt; 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 112), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 31), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+        pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((9 &lt;= floormod((threadIdx.x_1 + 31), 81)) &amp;&amp; (floormod((threadIdx.x_1 + 31), 81) &lt; 72)) &amp;&amp; (1 &lt;= floormod((threadIdx.x_1 + 4), 9))) &amp;&amp; (floormod((threadIdx.x_1 + 4), 9) &lt; 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 112), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 31), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+        attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
+        pad_temp.shared_1[(threadIdx.x_1 + 168)] = @tir.if_then_else((((9 &lt;= floormod((threadIdx.x_1 + 6), 81)) &amp;&amp; (1 &lt;= floormod((threadIdx.x_1 + 6), 9))) &amp;&amp; (floormod((threadIdx.x_1 + 6), 9) &lt; 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 168), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 6), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+        attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
+        pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((9 &lt;= floormod((threadIdx.x_1 + 62), 81)) &amp;&amp; (floormod((threadIdx.x_1 + 62), 81) &lt; 72)) &amp;&amp; (1 &lt;= floormod((threadIdx.x_1 + 8), 9))) &amp;&amp; (floormod((threadIdx.x_1 + 8), 9) &lt; 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 62), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+        attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
+        if @tir.likely((threadIdx.x_1 &lt; 44), dtype=bool) {
+          pad_temp.shared_1[(threadIdx.x_1 + 280)] = @tir.if_then_else((((threadIdx.x_1 &lt; 35) &amp;&amp; (1 &lt;= floormod((threadIdx.x_1 + 1), 9))) &amp;&amp; (floormod((threadIdx.x_1 + 1), 9) &lt; 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 280), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 37), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
         }
         attr [IterVar(threadIdx.x_2: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
-        kernel.shared_1: Buffer(kernel.shared, float32, [288], [], scope=&quot;shared&quot;)[threadIdx.x_2] = kernel[((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 18))]
+        kernel.shared_1: Buffer(kernel.shared, float32, [1152], [], scope=&quot;shared&quot;)[threadIdx.x_2] = kernel[((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 36)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 36))]
         attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
-        kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 56), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 18))]
+        kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 56), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 36), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
         attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
-        kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 112), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 18))]
+        kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 36)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 36))]
         attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
-        kernel.shared_1[(threadIdx.x_2 + 168)] = kernel[((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 168), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 6), 18))]
+        kernel.shared_1[(threadIdx.x_2 + 168)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 168), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 24), 36), 9)*9)) + floormod((threadIdx.x_2 + 6), 9))]
         attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
-        kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 224), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 18))]
+        kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 36)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 36))]
         attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
-        if @tir.likely((threadIdx.x_2 &lt; 8), dtype=bool) {
-          kernel.shared_1[(threadIdx.x_2 + 280)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 280), 18)*4608)) + cse_var_1) + threadIdx.x_2) + 10)]
-        }
-        for (rc.outer.inner: int32, 0, 2) {
-          for (ry.outer.inner: int32, 0, 3) {
-            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3))]))
-            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3))]))
-            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3))]))
-            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3))]))
-            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3))]))
-            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3))]))
-            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3))]))
-            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 18)]))
-            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 18)]))
-            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 18)]))
-            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 18)]))
-            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 18)]))
-            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 18)]))
-            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 18)]))
-            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 1)]))
-            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 1)]))
-            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 1)]))
-            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 1)]))
-            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 1)]))
-            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 1)]))
-            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 1)]))
-            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 19)]))
-            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 19)]))
-            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 19)]))
-            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 19)]))
-            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 19)]))
-            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 19)]))
-            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 19)]))
-            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 2)]))
-            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 2)]))
-            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 2)]))
-            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 2)]))
-            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 2)]))
-            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 2)]))
-            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 2)]))
-            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 20)]))
-            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 20)]))
-            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 20)]))
-            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 20)]))
-            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 20)]))
-            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 20)]))
-            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 20)]))
-          }
+        kernel.shared_1[(threadIdx.x_2 + 280)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 280), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 28), 36), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
+        kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 12), 36), 9)*9)) + floormod((threadIdx.x_2 + 3), 9))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
+        kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 392), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 36), 9)*9)) + floormod((threadIdx.x_2 + 5), 9))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
+        kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 36), 9)*9)) + floormod((threadIdx.x_2 + 7), 9))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
+        kernel.shared_1[(threadIdx.x_2 + 504)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 36)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 36)) + 64512)]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
+        kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 36), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
+        kernel.shared_1[(threadIdx.x_2 + 616)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 616), 36)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 36))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
+        kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 672), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 24), 36), 9)*9)) + floormod((threadIdx.x_2 + 6), 9))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
+        kernel.shared_1[(threadIdx.x_2 + 728)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 728), 36)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 36))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
+        kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 784), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 28), 36), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
+        kernel.shared_1[(threadIdx.x_2 + 840)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 840), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 12), 36), 9)*9)) + floormod((threadIdx.x_2 + 3), 9))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
+        kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 896), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 36), 9)*9)) + floormod((threadIdx.x_2 + 5), 9))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
+        kernel.shared_1[(threadIdx.x_2 + 952)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 952), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 36), 9)*9)) + floormod((threadIdx.x_2 + 7), 9))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
+        kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 36)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 36)) + 129024)]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
+        kernel.shared_1[(threadIdx.x_2 + 1064)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1064), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 36), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
+        if @tir.likely((threadIdx.x_2 &lt; 32), dtype=bool) {
+          kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1120), 36)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 36))]
         }
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 7)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
+        conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[floormod(threadIdx.x, 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 576)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 9)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
+        conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 576)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
+        conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 576)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
+        conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 576)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
+        conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 576)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
+        conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 576)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
+        conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 576)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
+        conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 577)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
+        conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 577)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
+        conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 577)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
+        conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 577)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
+        conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 577)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
+        conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 577)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
+        conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 577)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
+        conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 578)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
+        conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 578)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
+        conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 578)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
+        conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 578)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
+        conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 578)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
+        conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 578)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
+        conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 578)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[floormod(threadIdx.x, 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
+        conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[floormod(threadIdx.x, 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 612)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
+        conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 612)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
+        conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 612)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
+        conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 612)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
+        conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 612)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
+        conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 612)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
+        conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 612)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
+        conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 613)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
+        conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 613)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
+        conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 613)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
+        conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 613)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
+        conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 613)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
+        conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 613)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
+        conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 613)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
+        conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 614)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
+        conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 614)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
+        conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 614)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
+        conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 614)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
+        conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 614)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
+        conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 614)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
+        conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 614)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
+        conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 579)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
+        conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 579)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
+        conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 579)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
+        conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 579)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
+        conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 579)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
+        conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 579)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
+        conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 579)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
+        conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 580)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
+        conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 580)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
+        conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 580)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
+        conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 580)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
+        conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 580)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
+        conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 580)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
+        conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 580)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
+        conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 581)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
+        conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 581)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
+        conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 581)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
+        conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 581)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
+        conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 581)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
+        conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 581)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
+        conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 581)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
+        conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 615)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
+        conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 615)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
+        conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 615)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
+        conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 615)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
+        conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 615)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
+        conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 615)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
+        conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 615)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
+        conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 616)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
+        conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 616)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
+        conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 616)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
+        conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 616)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
+        conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 616)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
+        conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 616)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
+        conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 616)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
+        conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 617)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
+        conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 617)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
+        conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 617)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
+        conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 617)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
+        conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 617)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
+        conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 617)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
+        conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 617)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
+        conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 582)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
+        conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 582)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
+        conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 582)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
+        conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 582)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
+        conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 582)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
+        conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 582)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 72)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
+        conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 72)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 582)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
+        conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 583)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
+        conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 583)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
+        conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 583)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
+        conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 583)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
+        conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 583)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
+        conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 583)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 73)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
+        conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 73)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 583)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
+        conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 584)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
+        conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 584)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
+        conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 584)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
+        conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 584)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
+        conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 584)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
+        conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 584)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 74)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
+        conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 74)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 584)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
+        conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 618)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
+        conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 618)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
+        conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 618)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
+        conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 618)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
+        conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 618)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
+        conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 618)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 72)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
+        conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 72)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 618)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
+        conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 619)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
+        conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 619)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
+        conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 619)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
+        conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 619)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
+        conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 619)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
+        conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 619)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 73)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
+        conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 73)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 619)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
+        conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 620)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
+        conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 620)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
+        conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 620)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
+        conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 620)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
+        conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 620)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
+        conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 620)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 74)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
+        conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 74)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 620)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
+        conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 585)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
+        conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 585)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
+        conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 585)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
+        conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 585)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
+        conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 585)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
+        conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 585)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
+        conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 585)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
+        conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 586)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
+        conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 586)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
+        conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 586)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
+        conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 586)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
+        conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 586)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
+        conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 586)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
+        conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 586)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
+        conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 587)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
+        conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 587)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
+        conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 587)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
+        conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 587)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
+        conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 587)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
+        conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 587)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
+        conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 587)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
+        conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 621)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
+        conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 621)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
+        conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 621)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
+        conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 621)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
+        conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 621)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
+        conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 621)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
+        conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 621)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
+        conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 622)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
+        conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 622)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
+        conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 622)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
+        conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 622)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
+        conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 622)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
+        conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 622)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
+        conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 622)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
+        conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 623)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
+        conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 623)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
+        conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 623)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
+        conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 623)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
+        conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 623)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
+        conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 623)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
+        conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 623)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
+        conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 588)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
+        conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 588)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
+        conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 588)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
+        conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 588)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
+        conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 588)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
+        conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 588)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
+        conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 588)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
+        conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 589)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
+        conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 589)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
+        conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 589)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
+        conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 589)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
+        conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 589)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
+        conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 589)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
+        conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 589)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
+        conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 590)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
+        conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 590)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
+        conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 590)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
+        conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 590)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
+        conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 590)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
+        conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 590)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
+        conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 590)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
+        conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 624)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
+        conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 624)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
+        conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 624)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
+        conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 624)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
+        conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 624)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
+        conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 624)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
+        conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 624)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
+        conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 625)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
+        conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 625)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
+        conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 625)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
+        conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 625)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
+        conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 625)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
+        conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 625)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
+        conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 625)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
+        conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 626)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
+        conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 626)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
+        conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 626)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
+        conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 626)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
+        conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 626)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
+        conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 626)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
+        conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 626)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
+        conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 591)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
+        conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 591)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
+        conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 591)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
+        conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 591)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
+        conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 591)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
+        conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 591)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
+        conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 591)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
+        conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 592)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
+        conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 592)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
+        conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 592)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
+        conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 592)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
+        conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 592)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
+        conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 592)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 154)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
+        conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 154)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 592)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
+        conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 593)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
+        conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 593)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
+        conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 593)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
+        conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 593)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
+        conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 593)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
+        conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 593)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 155)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
+        conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 155)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 593)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
+        conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 627)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
+        conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 627)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
+        conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 627)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
+        conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 627)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
+        conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 627)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
+        conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 627)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
+        conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 627)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
+        conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 628)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
+        conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 628)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
+        conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 628)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
+        conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 628)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
+        conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 628)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
+        conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 628)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 154)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
+        conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 154)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 628)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
+        conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 629)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
+        conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 629)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
+        conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 629)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
+        conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 629)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
+        conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 629)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
+        conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 629)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 155)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
+        conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 155)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 629)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
+        conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 594)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
+        conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 594)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
+        conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 594)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
+        conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 594)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
+        conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 594)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
+        conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 594)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
+        conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 594)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
+        conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 595)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
+        conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 595)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
+        conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 595)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
+        conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 595)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
+        conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 595)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
+        conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 595)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
+        conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 595)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
+        conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 596)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
+        conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 596)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
+        conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 596)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
+        conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 596)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
+        conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 596)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
+        conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 596)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
+        conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 596)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
+        conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 630)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
+        conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 630)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
+        conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 630)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
+        conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 630)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
+        conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 630)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
+        conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 630)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
+        conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 630)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
+        conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 631)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
+        conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 631)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
+        conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 631)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
+        conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 631)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
+        conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 631)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
+        conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 631)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
+        conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 631)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
+        conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 632)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
+        conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 632)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
+        conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 632)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
+        conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 632)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
+        conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 632)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
+        conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 632)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
+        conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 632)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
+        conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 597)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
+        conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 597)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
+        conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 597)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
+        conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 597)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
+        conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 597)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
+        conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 597)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 225)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
+        conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 225)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 597)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
+        conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 598)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
+        conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 598)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
+        conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 598)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
+        conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 598)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
+        conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 598)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
+        conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 598)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 226)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
+        conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 226)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 598)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
+        conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 599)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
+        conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 599)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
+        conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 599)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
+        conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 599)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
+        conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 599)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
+        conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 599)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 227)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
+        conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 227)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 599)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
+        conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 633)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
+        conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 633)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
+        conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 633)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
+        conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 633)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
+        conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 633)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
+        conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 633)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 225)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
+        conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 225)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 633)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
+        conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 634)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
+        conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 634)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
+        conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 634)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
+        conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 634)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
+        conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 634)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
+        conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 634)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 226)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
+        conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 226)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 634)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
+        conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 635)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
+        conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 635)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
+        conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 635)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
+        conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 635)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
+        conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 635)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
+        conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 635)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 227)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
+        conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 227)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 635)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
+        conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 600)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
+        conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 600)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
+        conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 600)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
+        conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 600)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
+        conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 600)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 225)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
+        conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 225)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 600)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 234)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
+        conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 234)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 600)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
+        conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 601)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
+        conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 601)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
+        conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 601)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
+        conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 601)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
+        conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 601)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 226)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
+        conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 226)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 601)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 235)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
+        conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 235)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 601)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
+        conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 602)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
+        conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 602)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
+        conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 602)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
+        conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 602)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
+        conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 602)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 227)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
+        conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 227)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 602)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 236)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
+        conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 236)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 602)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
+        conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 636)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
+        conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 636)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
+        conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 636)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
+        conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 636)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
+        conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 636)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 225)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
+        conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 225)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 636)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 234)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
+        conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 234)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 636)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
+        conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 637)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
+        conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 637)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
+        conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 637)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
+        conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 637)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
+        conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 637)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 226)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
+        conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 226)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 637)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 235)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
+        conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 235)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 637)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
+        conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 638)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
+        conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 638)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
+        conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 638)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
+        conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 638)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
+        conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 638)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 227)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
+        conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 227)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 638)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 236)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
+        conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 236)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 638)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
+        conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 603)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
+        conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 603)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
+        conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 603)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
+        conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 603)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
+        conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 603)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
+        conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 603)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
+        conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 603)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
+        conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 604)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
+        conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 604)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
+        conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 604)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
+        conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 604)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
+        conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 604)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
+        conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 604)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
+        conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 604)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
+        conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 605)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
+        conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 605)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
+        conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 605)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
+        conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 605)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
+        conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 605)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
+        conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 605)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
+        conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 605)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
+        conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 639)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
+        conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 639)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
+        conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 639)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
+        conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 639)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
+        conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 639)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
+        conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 639)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
+        conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 639)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
+        conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 640)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
+        conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 640)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
+        conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 640)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
+        conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 640)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
+        conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 640)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
+        conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 640)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
+        conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 640)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
+        conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 641)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
+        conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 641)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
+        conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 641)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
+        conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 641)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
+        conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 641)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
+        conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 641)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
+        conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 641)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
+        conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 606)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
+        conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 606)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
+        conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 606)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
+        conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 606)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
+        conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 606)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
+        conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 606)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 306)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
+        conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 306)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 606)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
+        conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 607)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
+        conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 607)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
+        conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 607)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
+        conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 607)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
+        conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 607)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
+        conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 607)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 307)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
+        conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 307)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 607)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
+        conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 608)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
+        conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 608)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
+        conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 608)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
+        conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 608)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
+        conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 608)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
+        conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 608)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 308)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
+        conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 308)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 608)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
+        conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 642)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
+        conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 642)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
+        conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 642)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
+        conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 642)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
+        conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 642)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
+        conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 642)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 306)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
+        conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 306)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 642)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
+        conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 643)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
+        conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 643)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
+        conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 643)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
+        conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 643)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
+        conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 643)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
+        conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 643)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 307)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
+        conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 307)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 643)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
+        conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 644)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
+        conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 644)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
+        conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 644)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
+        conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 644)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
+        conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 644)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
+        conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 644)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 308)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
+        conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 308)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 644)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
+        conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 609)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
+        conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 609)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
+        conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 609)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
+        conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 609)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
+        conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 609)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 306)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
+        conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 306)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 609)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 315)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
+        conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 315)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 609)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
+        conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 610)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
+        conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 610)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
+        conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 610)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
+        conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 610)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
+        conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 610)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 307)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
+        conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 307)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 610)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
+        conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 610)]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
+        conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 611)]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
+        conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 611)]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
+        conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 611)]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
+        conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 611)]))
+        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
+        conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 611)]))
+        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 308)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
+        conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 308)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 611)]))
+        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
+        conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 611)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
+        conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 645)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
+        conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 645)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
+        conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 645)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
+        conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 645)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
+        conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 645)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 306)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
+        conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 306)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 645)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 315)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
+        conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 315)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 645)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
+        conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 646)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
+        conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 646)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
+        conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 646)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
+        conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 646)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
+        conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 646)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 307)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
+        conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 307)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 646)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
+        conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 646)]))
+        conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
+        conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 647)]))
+        conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
+        conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 647)]))
+        conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
+        conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 647)]))
+        conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
+        conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 647)]))
+        conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
+        conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 647)]))
+        conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 308)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
+        conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 308)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 647)]))
+        conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
+        conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 647)]))
       }
     }
     for (i1.inner: int32, 0, 2) {
       for (i2.inner: int32, 0, 7) {
-        compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[((i1.inner*7) + i2.inner)] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+        let cse_var_3: int32 = ((i1.inner*7) + i2.inner)
+         {
+          compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[cse_var_3] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+          compute[((((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7)) + 784)] = max((conv2d_nchw_1[(cse_var_3 + 14)] + bias[((((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner) + 16)]), 0f32)
+        }
       }
     }
   }
@@ -624,7 +1640,7 @@ 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: 0.402 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.378 ms
 </pre></div>
 </div>
 </div>
@@ -653,10 +1669,10 @@ conv2d_nchw_nn_o_i, conv2d_nchw_nn_i = s[conv2d_nchw].split(conv2d_nchw_nn, fact
 conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
 conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
 conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
-conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
-conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
+conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
+conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=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=8)
-conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
+conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=2)
 conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=7)
 conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
 conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
@@ -666,18 +1682,18 @@ conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o
 conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
 conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
 conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=1)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
 conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
 conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
-conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
-conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+conv2d_nchw_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=8)
-compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
+compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
 compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=7)
 compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
 compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
@@ -709,7 +1725,7 @@ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fus
 s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
 pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
 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;, 64)
+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:
@@ -728,89 +1744,1084 @@ CUDA source code:
   #define uint64_t unsigned long long
 #endif
 extern &quot;C&quot; __global__ void __launch_bounds__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
-  float conv2d_nchw[14];
-  __shared__ float pad_temp_shared[162];
-  __shared__ float kernel_shared[288];
+  float conv2d_nchw[28];
+  __shared__ float pad_temp_shared[324];
+  __shared__ float kernel_shared[1152];
   conv2d_nchw[0] = 0.000000e+00f;
+  conv2d_nchw[14] = 0.000000e+00f;
   conv2d_nchw[1] = 0.000000e+00f;
+  conv2d_nchw[15] = 0.000000e+00f;
   conv2d_nchw[2] = 0.000000e+00f;
+  conv2d_nchw[16] = 0.000000e+00f;
   conv2d_nchw[3] = 0.000000e+00f;
+  conv2d_nchw[17] = 0.000000e+00f;
   conv2d_nchw[4] = 0.000000e+00f;
+  conv2d_nchw[18] = 0.000000e+00f;
   conv2d_nchw[5] = 0.000000e+00f;
+  conv2d_nchw[19] = 0.000000e+00f;
   conv2d_nchw[6] = 0.000000e+00f;
+  conv2d_nchw[20] = 0.000000e+00f;
   conv2d_nchw[7] = 0.000000e+00f;
+  conv2d_nchw[21] = 0.000000e+00f;
   conv2d_nchw[8] = 0.000000e+00f;
+  conv2d_nchw[22] = 0.000000e+00f;
   conv2d_nchw[9] = 0.000000e+00f;
+  conv2d_nchw[23] = 0.000000e+00f;
   conv2d_nchw[10] = 0.000000e+00f;
+  conv2d_nchw[24] = 0.000000e+00f;
   conv2d_nchw[11] = 0.000000e+00f;
+  conv2d_nchw[25] = 0.000000e+00f;
   conv2d_nchw[12] = 0.000000e+00f;
+  conv2d_nchw[26] = 0.000000e+00f;
   conv2d_nchw[13] = 0.000000e+00f;
-  for (int rc_outer_outer = 0; rc_outer_outer &lt; 256; ++rc_outer_outer) {
+  conv2d_nchw[27] = 0.000000e+00f;
+  for (int rc_outer_outer = 0; rc_outer_outer &lt; 128; ++rc_outer_outer) {
     __syncthreads();
-    pad_temp_shared[((int)threadIdx.x)] = ((((9 &lt;= ((int)threadIdx.x)) &amp;&amp; (1 &lt;= (((int)threadIdx.x) % 9))) &amp;&amp; ((((int)threadIdx.x) % 9) &lt; 8)) ? data[((((rc_outer_outer * 98) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
-    pad_temp_shared[(((int)threadIdx.x) + 56)] = (((((9 &lt;= ((((int)threadIdx.x) + 56) % 81)) &amp;&amp; (((((int)threadIdx.x) + 56) % 81) &lt; 72)) &amp;&amp; (1 &lt;= ((((int)threadIdx.x) + 2) % 9))) &amp;&amp; (((((int)threadIdx.x) + 2) % 9) &lt; 8)) ? data[(((((rc_outer_outer * 98) + (((((int)threadIdx.x) + 56) / 81) * 49)) + ((((((int)threadIdx.x) + 56) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
-    if (((int)threadIdx.x) &lt; 50) {
-      pad_temp_shared[(((int)threadIdx.x) + 112)] = ((((((int)threadIdx.x) &lt; 41) &amp;&amp; (1 &lt;= ((((int)threadIdx.x) + 4) % 9))) &amp;&amp; (((((int)threadIdx.x) + 4) % 9) &lt; 8)) ? data[(((((rc_outer_outer * 98) + (((((int)threadIdx.x) + 112) / 81) * 49)) + (((((int)threadIdx.x) + 31) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+    pad_temp_shared[((int)threadIdx.x)] = ((((9 &lt;= ((int)threadIdx.x)) &amp;&amp; (1 &lt;= (((int)threadIdx.x) % 9))) &amp;&amp; ((((int)threadIdx.x) % 9) &lt; 8)) ? data[((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+    pad_temp_shared[(((int)threadIdx.x) + 56)] = (((((9 &lt;= ((((int)threadIdx.x) + 56) % 81)) &amp;&amp; (((((int)threadIdx.x) + 56) % 81) &lt; 72)) &amp;&amp; (1 &lt;= ((((int)threadIdx.x) + 2) % 9))) &amp;&amp; (((((int)threadIdx.x) + 2) % 9) &lt; 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 56) / 81) * 49)) + ((((((int)threadIdx.x) + 56) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+    pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((9 &lt;= ((((int)threadIdx.x) + 31) % 81)) &amp;&amp; (((((int)threadIdx.x) + 31) % 81) &lt; 72)) &amp;&amp; (1 &lt;= ((((int)threadIdx.x) + 4) % 9))) &amp;&amp; (((((int)threadIdx.x) + 4) % 9) &lt; 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 112) / 81) * 49)) + ((((((int)threadIdx.x) + 31) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+    pad_temp_shared[(((int)threadIdx.x) + 168)] = ((((3 &lt;= ((int)threadIdx.x)) &amp;&amp; (1 &lt;= ((((int)threadIdx.x) + 6) % 9))) &amp;&amp; (((((int)threadIdx.x) + 6) % 9) &lt; 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 168) / 81) * 49)) + (((((int)threadIdx.x) + 6) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+    pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((9 &lt;= ((((int)threadIdx.x) + 62) % 81)) &amp;&amp; (((((int)threadIdx.x) + 62) % 81) &lt; 72)) &amp;&amp; (1 &lt;= ((((int)threadIdx.x) + 8) % 9))) &amp;&amp; (((((int)threadIdx.x) + 8) % 9) &lt; 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 224) / 81) * 49)) + ((((((int)threadIdx.x) + 62) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+    if (((int)threadIdx.x) &lt; 44) {
+      pad_temp_shared[(((int)threadIdx.x) + 280)] = ((((((int)threadIdx.x) &lt; 35) &amp;&amp; (1 &lt;= ((((int)threadIdx.x) + 1) % 9))) &amp;&amp; (((((int)threadIdx.x) + 1) % 9) &lt; 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 280) / 81) * 49)) + (((((int)threadIdx.x) + 37) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
     }
-    kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 18)) + (((int)threadIdx.x) % 18))];
-    kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 2) % 18))];
-    kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 4) % 18))];
-    kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 168) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 6) % 18))];
-    kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 8) % 18))];
-    if (((int)threadIdx.x) &lt; 8) {
-      kernel_shared[(((int)threadIdx.x) + 280)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 280) / 18) * 4608)) + (rc_outer_outer * 18)) + ((int)threadIdx.x)) + 10)];
+    kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) % 36))];
+    kernel_shared[(((int)threadIdx.x) + 56)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 56) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 20) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
+    kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 4) % 36))];
+    kernel_shared[(((int)threadIdx.x) + 168)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 168) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 24) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 6) % 9))];
+    kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 8) % 36))];
+    kernel_shared[(((int)threadIdx.x) + 280)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 280) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 28) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
+    kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 12) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 3) % 9))];
+    kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 32) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 5) % 9))];
+    kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 16) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 7) % 9))];
+    kernel_shared[(((int)threadIdx.x) + 504)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) % 36)) + 64512)];
+    kernel_shared[(((int)threadIdx.x) + 560)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 20) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
+    kernel_shared[(((int)threadIdx.x) + 616)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 616) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 4) % 36))];
+    kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 672) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 24) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 6) % 9))];
+    kernel_shared[(((int)threadIdx.x) + 728)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 728) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 8) % 36))];
+    kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 28) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
+    kernel_shared[(((int)threadIdx.x) + 840)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 840) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 12) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 3) % 9))];
+    kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 896) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 32) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 5) % 9))];
+    kernel_shared[(((int)threadIdx.x) + 952)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 952) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 16) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 7) % 9))];
+    kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) % 36)) + 129024)];
+    kernel_shared[(((int)threadIdx.x) + 1064)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1064) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 20) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
+    if (((int)threadIdx.x) &lt; 32) {
+      kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1120) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 4))];
     }
     __syncthreads();
-    for (int rc_outer_inner = 0; rc_outer_inner &lt; 2; ++rc_outer_inner) {
-      for (int ry_outer_inner = 0; ry_outer_inner &lt; 3; ++ry_outer_inner) {
-        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3))]));
-        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3))]));
-        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3))]));
-        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3))]));
-        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3))]));
-        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3))]));
-        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3))]));
-        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 18)]));
-        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 18)]));
-        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 18)]));
-        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 18)]));
-        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 18)]));
-        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 18)]));
-        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 18)]));
-        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 1)]));
-        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 1)]));
-        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 1)]));
-        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 1)]));
-        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 1)]));
-        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 1)]));
-        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 1)]));
-        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 19)]));
-        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 19)]));
-        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 19)]));
-        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 19)]));
-        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 19)]));
-        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 19)]));
-        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 19)]));
-        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 2)]));
-        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 2)]));
-        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 2)]));
-        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 2)]));
-        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 2)]));
-        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 2)]));
-        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 2)]));
-        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 20)]));
-        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 20)]));
-        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 20)]));
-        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 20)]));
-        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 20)]));
-        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 20)]));
-        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 20)]));
-      }
-    }
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 7)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
+    conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((int)threadIdx.x) % 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 576)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
+    conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 576)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
+    conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 576)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
+    conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 576)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
+    conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 576)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
+    conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 576)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
+    conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 576)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
+    conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 577)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
+    conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 577)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
+    conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 577)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
+    conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 577)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
+    conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 577)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
+    conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 577)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
+    conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 577)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
+    conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 578)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
+    conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 578)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
+    conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 578)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
+    conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 578)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
+    conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 578)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
+    conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 578)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
+    conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 578)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) % 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
+    conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((int)threadIdx.x) % 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 612)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
+    conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 612)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
+    conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 612)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
+    conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 612)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
+    conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 612)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
+    conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 612)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
+    conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 612)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
+    conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 613)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
+    conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 613)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
+    conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 613)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
+    conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 613)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
+    conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 613)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
+    conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 613)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
+    conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 613)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
+    conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 614)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
+    conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 614)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
+    conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 614)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
+    conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 614)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
+    conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 614)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
+    conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 614)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
+    conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 614)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
+    conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 579)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
+    conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 579)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
+    conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 579)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
+    conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 579)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
+    conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 579)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
+    conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 579)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
+    conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 579)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
+    conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 580)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
+    conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 580)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
+    conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 580)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
+    conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 580)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
+    conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 580)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
+    conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 580)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
+    conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 580)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
+    conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 581)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
+    conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 581)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
+    conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 581)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
+    conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 581)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
+    conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 581)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
+    conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 581)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
+    conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 581)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
+    conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 615)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
+    conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 615)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
+    conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 615)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
+    conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 615)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
+    conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 615)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
+    conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 615)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
+    conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 615)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
+    conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 616)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
+    conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 616)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
+    conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 616)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
+    conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 616)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
+    conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 616)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
+    conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 616)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
+    conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 616)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
+    conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 617)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
+    conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 617)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
+    conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 617)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
+    conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 617)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
+    conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 617)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
+    conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 617)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
+    conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 617)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
+    conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 582)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
+    conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 582)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
+    conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 582)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
+    conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 582)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
+    conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 582)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
+    conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 582)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 72)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
+    conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 72)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 582)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
+    conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 583)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
+    conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 583)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
+    conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 583)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
+    conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 583)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
+    conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 583)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
+    conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 583)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 73)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
+    conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 73)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 583)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
+    conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 584)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
+    conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 584)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
+    conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 584)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
+    conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 584)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
+    conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 584)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
+    conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 584)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 74)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
+    conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 74)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 584)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
+    conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 618)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
+    conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 618)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
+    conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 618)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
+    conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 618)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
+    conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 618)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
+    conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 618)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 72)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
+    conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 72)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 618)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
+    conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 619)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
+    conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 619)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
+    conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 619)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
+    conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 619)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
+    conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 619)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
+    conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 619)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 73)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
+    conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 73)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 619)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
+    conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 620)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
+    conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 620)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
+    conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 620)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
+    conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 620)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
+    conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 620)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
+    conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 620)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 74)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
+    conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 74)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 620)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
+    conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 585)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
+    conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 585)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
+    conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 585)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
+    conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 585)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
+    conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 585)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
+    conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 585)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
+    conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 585)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
+    conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 586)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
+    conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 586)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
+    conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 586)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
+    conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 586)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
+    conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 586)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
+    conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 586)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
+    conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 586)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
+    conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 587)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
+    conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 587)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
+    conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 587)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
+    conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 587)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
+    conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 587)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
+    conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 587)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
+    conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 587)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
+    conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 621)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
+    conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 621)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
+    conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 621)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
+    conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 621)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
+    conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 621)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
+    conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 621)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
+    conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 621)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
+    conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 622)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
+    conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 622)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
+    conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 622)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
+    conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 622)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
+    conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 622)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
+    conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 622)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
+    conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 622)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
+    conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 623)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
+    conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 623)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
+    conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 623)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
+    conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 623)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
+    conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 623)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
+    conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 623)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
+    conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 623)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
+    conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 588)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
+    conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 588)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
+    conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 588)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
+    conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 588)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
+    conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 588)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
+    conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 588)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
+    conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 588)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
+    conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 589)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
+    conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 589)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
+    conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 589)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
+    conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 589)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
+    conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 589)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
+    conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 589)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
+    conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 589)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
+    conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 590)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
+    conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 590)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
+    conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 590)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
+    conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 590)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
+    conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 590)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
+    conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 590)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
+    conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 590)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
+    conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 624)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
+    conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 624)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
+    conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 624)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
+    conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 624)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
+    conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 624)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
+    conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 624)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
+    conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 624)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
+    conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 625)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
+    conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 625)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
+    conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 625)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
+    conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 625)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
+    conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 625)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
+    conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 625)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
+    conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 625)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
+    conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 626)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
+    conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 626)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
+    conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 626)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
+    conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 626)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
+    conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 626)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
+    conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 626)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
+    conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 626)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
+    conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 591)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
+    conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 591)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
+    conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 591)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
+    conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 591)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
+    conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 591)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
+    conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 591)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
+    conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 591)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
+    conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 592)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
+    conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 592)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
+    conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 592)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
+    conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 592)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
+    conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 592)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
+    conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 592)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 154)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
+    conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 154)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 592)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
+    conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 593)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
+    conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 593)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
+    conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 593)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
+    conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 593)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
+    conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 593)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
+    conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 593)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 155)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
+    conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 155)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 593)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
+    conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 627)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
+    conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 627)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
+    conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 627)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
+    conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 627)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
+    conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 627)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
+    conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 627)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
+    conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 627)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
+    conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 628)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
+    conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 628)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
+    conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 628)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
+    conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 628)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
+    conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 628)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
+    conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 628)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 154)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
+    conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 154)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 628)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
+    conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 629)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
+    conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 629)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
+    conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 629)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
+    conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 629)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
+    conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 629)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
+    conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 629)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 155)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
+    conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 155)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 629)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 162)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
+    conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 162)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 594)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 171)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
+    conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 171)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 594)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
+    conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 594)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
+    conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 594)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
+    conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 594)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
+    conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 594)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
+    conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 594)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 163)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
+    conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 163)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 595)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
+    conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 595)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
+    conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 595)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
+    conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 595)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
+    conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 595)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
+    conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 595)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
+    conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 595)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
+    conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 596)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
+    conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 596)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
+    conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 596)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
+    conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 596)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
+    conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 596)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
+    conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 596)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
+    conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 596)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 162)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
+    conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 162)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 630)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 171)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
+    conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 171)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 630)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
+    conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 630)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
+    conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 630)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
+    conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 630)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
+    conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 630)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
+    conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 630)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 163)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
+    conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 163)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 631)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
+    conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 631)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
+    conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 631)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
+    conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 631)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
+    conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 631)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
+    conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 631)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
+    conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 631)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
+    conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 632)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
+    conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 632)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
+    conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 632)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
+    conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 632)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
+    conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 632)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
+    conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 632)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
+    conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 632)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 171)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
+    conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 171)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 597)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
+    conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 597)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
+    conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 597)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
+    conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 597)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
+    conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 597)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
+    conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 597)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 225)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
+    conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 225)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 597)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
+    conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 598)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
+    conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 598)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
+    conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 598)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
+    conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 598)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
+    conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 598)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
+    conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 598)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 226)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
+    conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 226)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 598)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
+    conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 599)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
+    conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 599)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
+    conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 599)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
+    conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 599)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
+    conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 599)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
+    conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 599)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 227)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
+    conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 227)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 599)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 171)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
+    conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 171)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 633)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
+    conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 633)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
+    conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 633)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
+    conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 633)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
+    conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 633)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
+    conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 633)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 225)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
+    conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 225)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 633)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
+    conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 634)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
+    conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 634)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
+    conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 634)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
+    conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 634)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
+    conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 634)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
+    conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 634)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 226)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
+    conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 226)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 634)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
+    conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 635)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
+    conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 635)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
+    conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 635)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
+    conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 635)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
+    conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 635)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
+    conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 635)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 227)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
+    conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 227)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 635)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
+    conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 600)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
+    conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 600)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
+    conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 600)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
+    conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 600)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
+    conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 600)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 225)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
+    conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 225)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 600)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 234)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
+    conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 234)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 600)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
+    conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 601)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
+    conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 601)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
+    conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 601)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
+    conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 601)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
+    conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 601)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 226)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
+    conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 226)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 601)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 235)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
+    conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 235)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 601)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
+    conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 602)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
+    conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 602)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
+    conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 602)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
+    conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 602)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
+    conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 602)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 227)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
+    conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 227)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 602)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 236)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
+    conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 236)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 602)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
+    conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 636)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
+    conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 636)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
+    conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 636)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
+    conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 636)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
+    conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 636)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 225)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
+    conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 225)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 636)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 234)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
+    conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 234)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 636)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
+    conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 637)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
+    conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 637)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
+    conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 637)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
+    conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 637)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
+    conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 637)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 226)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
+    conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 226)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 637)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 235)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
+    conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 235)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 637)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
+    conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 638)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
+    conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 638)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
+    conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 638)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
+    conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 638)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
+    conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 638)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 227)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
+    conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 227)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 638)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 236)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
+    conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 236)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 638)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 243)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
+    conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 243)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 603)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
+    conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 603)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
+    conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 603)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
+    conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 603)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
+    conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 603)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
+    conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 603)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
+    conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 603)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 244)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
+    conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 244)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 604)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
+    conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 604)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
+    conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 604)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
+    conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 604)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
+    conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 604)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
+    conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 604)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
+    conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 604)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
+    conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 605)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
+    conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 605)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
+    conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 605)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
+    conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 605)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
+    conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 605)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
+    conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 605)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
+    conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 605)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 243)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
+    conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 243)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 639)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
+    conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 639)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
+    conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 639)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
+    conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 639)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
+    conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 639)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
+    conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 639)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
+    conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 639)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 244)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
+    conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 244)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 640)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
+    conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 640)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
+    conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 640)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
+    conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 640)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
+    conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 640)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
+    conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 640)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
+    conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 640)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
+    conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 641)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
+    conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 641)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
+    conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 641)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
+    conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 641)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
+    conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 641)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
+    conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 641)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
+    conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 641)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
+    conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 606)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
+    conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 606)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
+    conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 606)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
+    conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 606)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
+    conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 606)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
+    conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 606)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 306)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
+    conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 306)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 606)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
+    conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 607)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
+    conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 607)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
+    conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 607)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
+    conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 607)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
+    conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 607)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
+    conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 607)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 307)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
+    conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 307)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 607)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
+    conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 608)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
+    conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 608)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
+    conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 608)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
+    conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 608)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
+    conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 608)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
+    conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 608)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 308)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
+    conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 308)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 608)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
+    conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 642)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
+    conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 642)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
+    conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 642)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
+    conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 642)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
+    conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 642)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
+    conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 642)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 306)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
+    conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 306)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 642)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
+    conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 643)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
+    conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 643)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
+    conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 643)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
+    conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 643)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
+    conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 643)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
+    conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 643)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 307)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
+    conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 307)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 643)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
+    conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 644)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
+    conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 644)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
+    conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 644)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
+    conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 644)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
+    conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 644)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
+    conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 644)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 308)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
+    conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 308)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 644)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
+    conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 609)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
+    conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 609)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
+    conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 609)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
+    conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 609)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
+    conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 609)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 306)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
+    conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 306)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 609)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 315)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
+    conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 315)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 609)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
+    conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 610)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
+    conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 610)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
+    conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 610)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
+    conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 610)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
+    conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 610)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 307)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
+    conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 307)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 610)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
+    conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 610)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
+    conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 611)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
+    conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 611)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
+    conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 611)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
+    conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 611)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
+    conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 611)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 308)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
+    conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 308)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 611)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
+    conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 611)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
+    conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 645)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
+    conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 645)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
+    conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 645)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
+    conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 645)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
+    conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 645)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 306)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
+    conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 306)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 645)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 315)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
+    conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 315)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 645)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
+    conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 646)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
+    conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 646)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
+    conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 646)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
+    conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 646)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
+    conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 646)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 307)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
+    conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 307)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 646)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
+    conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 646)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
+    conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 647)]));
+    conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
+    conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 647)]));
+    conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
+    conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 647)]));
+    conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
+    conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 647)]));
+    conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
+    conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 647)]));
+    conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 308)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
+    conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 308)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 647)]));
+    conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
+    conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 647)]));
   }
   for (int i1_inner = 0; i1_inner &lt; 2; ++i1_inner) {
     for (int i2_inner = 0; i2_inner &lt; 7; ++i2_inner) {
-      compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[((i1_inner * 7) + i2_inner)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+      compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[((i1_inner * 7) + i2_inner)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+      compute[((((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7)) + 784)] = max((conv2d_nchw[(((i1_inner * 7) + i2_inner) + 14)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner) + 16)]), 0.000000e+00f);
     }
   }
 }
@@ -848,7 +2859,7 @@ In the example below we resume the status and do more 5 trials.</p>
 Get devices for measurement successfully!
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  15.021 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  22.385 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 138f81fb3..4caab4949 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -906,7 +906,7 @@ so we can read the log file and load the best schedules.</p>
 Evaluate inference time cost...
 Execution time summary:
  mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)
-   9.8413       9.8386       9.8801       9.8052       0.0306
+   9.7300       9.7563       9.7570       9.6767       0.0377
 </pre></div>
 </div>
 </div>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
index 8762cc95c..1c074b365 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -925,7 +925,7 @@ 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)
-  757.2458     757.1720     757.5069     757.0584      0.1904
+  762.7657     762.5522     763.3508     762.3940      0.4188
 </pre></div>
 </div>
 </div>
@@ -947,7 +947,7 @@ 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  21.767 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  23.952 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 c83dffde3..96f796d33 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -625,76 +625,30 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
              placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
              compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
   buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
-  preflattened_buffer_map = {placeholder_6: placeholder_15: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_5: placeholder_18: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], [])} {
-  for (i0.outer.i1.outer.fused: int32, 0, 32) &quot;parallel&quot; {
-    allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global {
-      for (nb_j.inner: int32, 0, 2) {
-        for (i.inner.init: int32, 0, 64) {
-          let cse_var_1: int32 = ((i.inner.init*32) + (nb_j.inner*16))
-           {
-            compute_5: Buffer(compute_4, float32, [2048], [])[cse_var_1] = 0f32
-            compute_5[(cse_var_1 + 1)] = 0f32
-            compute_5[(cse_var_1 + 2)] = 0f32
-            compute_5[(cse_var_1 + 3)] = 0f32
-            compute_5[(cse_var_1 + 4)] = 0f32
-            compute_5[(cse_var_1 + 5)] = 0f32
-            compute_5[(cse_var_1 + 6)] = 0f32
-            compute_5[(cse_var_1 + 7)] = 0f32
-            compute_5[(cse_var_1 + 8)] = 0f32
-            compute_5[(cse_var_1 + 9)] = 0f32
-            compute_5[(cse_var_1 + 10)] = 0f32
-            compute_5[(cse_var_1 + 11)] = 0f32
-            compute_5[(cse_var_1 + 12)] = 0f32
-            compute_5[(cse_var_1 + 13)] = 0f32
-            compute_5[(cse_var_1 + 14)] = 0f32
-            compute_5[(cse_var_1 + 15)] = 0f32
+  preflattened_buffer_map = {placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_5: placeholder_18: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], [])} {
+  for (i0.outer.i1.outer.fused: int32, 0, 128) &quot;parallel&quot; {
+    allocate(compute_4: Pointer(global float32), float32, [512]), storage_scope = global {
+      for (i.outer.inner: int32, 0, 4) {
+        for (i.inner.init: int32, 0, 8) {
+          for (j.init: int32, 0, 16) {
+            compute_5: Buffer(compute_4, float32, [512], [])[(((i.outer.inner*128) + (i.inner.init*16)) + j.init)] = 0f32
           }
         }
-        for (elem_idx: int32, 0, let cse_var_2: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
-          for (i.inner: int32, 0, 64) {
-            let cse_var_21: int32 = (elem_idx*16)
-            let cse_var_20: int32 = ((i.inner*32) + (nb_j.inner*16))
-            let cse_var_19: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
-            let cse_var_18: int32 = ((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i.inner*256))
-            let cse_var_17: int32 = (cse_var_20 + 9)
-            let cse_var_16: int32 = (cse_var_20 + 8)
-            let cse_var_15: int32 = (cse_var_20 + 7)
-            let cse_var_14: int32 = (cse_var_20 + 6)
-            let cse_var_13: int32 = (cse_var_20 + 5)
-            let cse_var_12: int32 = (cse_var_20 + 4)
-            let cse_var_11: int32 = (cse_var_20 + 3)
-            let cse_var_10: int32 = (cse_var_20 + 2)
-            let cse_var_9: int32 = (cse_var_20 + 15)
-            let cse_var_8: int32 = (cse_var_20 + 14)
-            let cse_var_7: int32 = (cse_var_20 + 13)
-            let cse_var_6: int32 = (cse_var_20 + 12)
-            let cse_var_5: int32 = (cse_var_20 + 11)
-            let cse_var_4: int32 = (cse_var_20 + 10)
-            let cse_var_3: int32 = (cse_var_20 + 1)
-             {
-              compute_5[cse_var_20] = (compute_5[cse_var_20] + (placeholder_1[((placeholder_3[cse_var_19]*16) + cse_var_21)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
-              compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
-              compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
-              compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
-              compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
-              compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
-              compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
-              compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
-              compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
-              compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
-              compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
-              compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
-              compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
-              compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
-              compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
-              compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+        for (elem_idx: int32, 0, let cse_var_1: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+          for (i.inner: int32, 0, 8) {
+            for (j: int32, 0, 16) {
+              let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32)
+              if @tir.likely((elem_idx &lt; (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+                let cse_var_3: int32 = (((i.outer.inner*128) + (i.inner*16)) + j)
+                compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + j)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+              }
             }
           }
         }
       }
-      for (i0.inner: int32, 0, 64) {
-        let cse_var_22: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
-        compute[ramp(cse_var_22, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
+      for (i0.inner: int32, 0, 32) {
+        let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
+        compute[ramp(cse_var_4, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_4, 1, 16)]), broadcast(0f32, 16))
       }
     }
   }
@@ -732,7 +686,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
 <span class="p">)</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.845 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.553 ms
 </pre></div>
 </div>
 <div class="admonition note">
diff --git a/docs/how_to/tune_with_autotvm/sg_execution_times.html b/docs/how_to/tune_with_autotvm/sg_execution_times.html
index 196c5b364..92d8d8da8 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -327,7 +327,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:45.953</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:46.289</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 84%" />
@@ -336,15 +336,15 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:45.917</p></td>
+<td><p>00:46.254</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
-<td><p>00:00.020</p></td>
+<td><p>00:00.019</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></td>
-<td><p>00:00.005</p></td>
+<td><p>00:00.006</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></td>
diff --git a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
index 81c6cafaf..4acf5fd7d 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -1436,8 +1436,8 @@ No: 8   GFLOPS: 0.00/0.00       result: Traceback (most recent call last):
 TimeoutError
 
         [(&#39;tile_f&#39;, [-1, 2, 1, 64]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 1, 4]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 0)],None,4909501
-No: 9   GFLOPS: 216.81/216.81   result: MeasureResult(costs=(0.001067741427586207,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.152261257171631, timestamp=1661498480.8726752)        [(&#39;tile_f&#39;, [-1, 1, 4, 8]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 2, 2]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 0)],None,5072689
-No: 10  GFLOPS: 0.00/216.81     result: Traceback (most recent call last):
+No: 9   GFLOPS: 192.94/192.94   result: MeasureResult(costs=(0.0011998708666666666,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.105665683746338, timestamp=1661510163.694395)        [(&#39;tile_f&#39;, [-1, 1, 4, 8]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 2, 2]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 0)],None,5072689
+No: 10  GFLOPS: 0.00/192.94     result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 588, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 540, in _build_func_common
@@ -1560,8 +1560,8 @@ Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 871, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
 tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 4, 4, 8]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 7]), (&#39;tile_rc&#39;, [-1, 64, 2]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 0)],None,5092711
-No: 11  GFLOPS: 259.30/259.30   result: MeasureResult(costs=(0.0008928053204419888,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6899151802062988, timestamp=1661498481.7430823)      [(&#39;tile_f&#39;, [-1, 8, 2, 1]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 2, 1]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 0)],None,4264713
-No: 12  GFLOPS: 0.00/259.30     result: Traceback (most recent call last):
+No: 11  GFLOPS: 261.08/261.08   result: MeasureResult(costs=(0.0008867000828729282,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4912402629852295, timestamp=1661510164.6044521)      [(&#39;tile_f&#39;, [-1, 8, 2, 1]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 2, 1]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 0)],None,4264713
+No: 12  GFLOPS: 0.00/261.08     result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 588, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 540, in _build_func_common
@@ -1684,7 +1684,7 @@ Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 871, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
 tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 128, 1, 2]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 1, 256]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 0)],None,183542
-No: 13  GFLOPS: 0.00/259.30     result: Traceback (most recent call last):
+No: 13  GFLOPS: 0.00/261.08     result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 588, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 540, in _build_func_common
@@ -1807,7 +1807,7 @@ Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 871, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
 tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 4, 8, 8]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 1, 64]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 0)],None,2482196
-No: 14  GFLOPS: 0.00/259.30     result: Traceback (most recent call last):
+No: 14  GFLOPS: 0.00/261.08     result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 588, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 540, in _build_func_common
@@ -1930,9 +1930,9 @@ Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 871, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
 tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 64, 1, 4]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 7]), (&#39;tile_rc&#39;, [-1, 4, 2]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 1)],None,10306226
-No: 15  GFLOPS: 5.38/259.30     result: MeasureResult(costs=(0.04303303925,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8491942882537842, timestamp=1661498486.278752)       [(&#39;tile_f&#39;, [-1, 2, 2, 8]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 4, 8]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 1)],None,5330964
-No: 16  GFLOPS: 3.34/259.30     result: MeasureResult(costs=(0.06941368025,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.516972303390503, timestamp=1661498487.5165503)       [(&#39;tile_f&#39;, [-1, 8, 4, 4]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#39;tile_x&#39;, [-1, 1, 1, 7]), (&#39;tile_rc&#39;, [-1, 4, 1]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 0)],None,2140058
-No: 17  GFLOPS: 0.00/259.30     result: Traceback (most recent call last):
+No: 15  GFLOPS: 5.46/261.08     result: MeasureResult(costs=(0.04238295375,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8740129470825195, timestamp=1661510169.2188017)      [(&#39;tile_f&#39;, [-1, 2, 2, 8]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 4, 8]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 1)],None,5330964
+No: 16  GFLOPS: 3.36/261.08     result: MeasureResult(costs=(0.06898508675,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.61911940574646, timestamp=1661510170.4581182)        [(&#39;tile_f&#39;, [-1, 8, 4, 4]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#39;tile_x&#39;, [-1, 1, 1, 7]), (&#39;tile_rc&#39;, [-1, 4, 1]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 0)],None,2140058
+No: 17  GFLOPS: 0.00/261.08     result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 142, in build
     res = future.result()
   File &quot;/usr/lib/python3.7/concurrent/futures/_base.py&quot;, line 435, in result
@@ -1950,8 +1950,8 @@ No: 17  GFLOPS: 0.00/259.30     result: Traceback (most recent call last):
 TimeoutError
 
         [(&#39;tile_f&#39;, [-1, 2, 2, 1]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 4, 16]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 1)],None,10195251
-No: 18  GFLOPS: 27.91/259.30    result: MeasureResult(costs=(0.008294080785714286,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3092622756958008, timestamp=1661498498.5817828)       [(&#39;tile_f&#39;, [-1, 4, 8, 4]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 1, 4]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 1)],None,6068603
-No: 19  GFLOPS: 0.00/259.30     result: Traceback (most recent call last):
+No: 18  GFLOPS: 26.09/261.08    result: MeasureResult(costs=(0.008873694833333333,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.168952465057373, timestamp=1661510181.3898182)        [(&#39;tile_f&#39;, [-1, 4, 8, 4]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 1, 4]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 1)],None,6068603
+No: 19  GFLOPS: 0.00/261.08     result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 588, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 540, in _build_func_common
@@ -2074,7 +2074,7 @@ Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 871, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
 tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 16, 4, 8]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 4, 128]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 1)],None,6956993
-No: 20  GFLOPS: 0.00/259.30     result: Traceback (most recent call last):
+No: 20  GFLOPS: 0.00/261.08     result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 588, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 540, in _build_func_common
@@ -2237,7 +2237,7 @@ and measure running time.</p>
 Best config:
 [(&#39;tile_f&#39;, [-1, 8, 2, 1]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 2, 1]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 0)],None,4264713
 Finish loading 20 records
-Time cost of this operator: 0.001262
+Time cost of this operator: 0.001254
 </pre></div>
 </div>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autotvm-tune-conv2d-cuda-py">
diff --git a/docs/how_to/work_with_microtvm/micro_autotune.html b/docs/how_to/work_with_microtvm/micro_autotune.html
index 0ce734ea0..dfb9084ae 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -584,10 +584,10 @@ the tuned operator.</p>
 ########## Build without Autotuning ##########
 Node Name                                     Ops                                           Time(us)  Time(%)  Shape              Inputs  Outputs  Measurements(us)
 ---------                                     ---                                           --------  -------  -----              ------  -------  ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  310.8     98.736   (1, 2, 10, 10, 3)  2       1        [310.8]
-tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       3.015     0.958    (1, 6, 10, 10)     1       1        [3.015]
-tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.964     0.306    (1, 1, 10, 10, 3)  1       1        [0.964]
-Total_time                                    -                                             314.779   -        -                  -       -        -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  308.9     98.728   (1, 2, 10, 10, 3)  2       1        [308.9]
+tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       3.017     0.964    (1, 6, 10, 10)     1       1        [3.017]
+tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.962     0.307    (1, 1, 10, 10, 3)  1       1        [0.962]
+Total_time                                    -                                             312.879   -        -                  -       -        -
 </pre></div>
 </div>
 </div>
@@ -640,10 +640,10 @@ Total_time                                    -
 ########## Build with Autotuning ##########
 Node Name                                     Ops                                           Time(us)  Time(%)  Shape              Inputs  Outputs  Measurements(us)
 ---------                                     ---                                           --------  -------  -----              ------  -------  ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  132.7     97.987   (1, 6, 10, 10, 1)  2       1        [132.7]
-tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       1.767     1.305    (1, 6, 10, 10)     1       1        [1.767]
-tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.96      0.709    (1, 1, 10, 10, 3)  1       1        [0.96]
-Total_time                                    -                                             135.426   -        -                  -       -        -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  193.0     98.646   (1, 6, 10, 10, 1)  2       1        [193.0]
+tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       1.808     0.924    (1, 6, 10, 10)     1       1        [1.808]
+tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.841     0.43     (1, 3, 10, 10, 1)  1       1        [0.841]
+Total_time                                    -                                             195.649   -        -                  -       -        -
 </pre></div>
 </div>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index a07cdd64d..65259f427 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -516,7 +516,7 @@ take about <strong>2 minutes</strong> to download the Stanford Cars, while COCO
 <a href="https://docs.python.org/3/library/shutil.html#shutil.move" title="shutil.move" class="sphx-glr-backref-module-shutil sphx-glr-backref-type-py-function"><span class="n">shutil</span><span class="o">.</span><span class="n">move</span></a><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;</span><span class="si">{</span><a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-typ [...]
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>&#39;/tmp/tmpgxo_i92h/images/random&#39;
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>&#39;/tmp/tmpx4ylsxc9/images/random&#39;
 </pre></div>
 </div>
 </div>
@@ -576,8 +576,8 @@ objects to other stuff? We can display some examples from our datasets using <co
     <span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">&quot;off&quot;</span><span class="p">)</span>
 </pre></div>
 </div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpgxo_i92h/images/target contains 8144 images
-/tmp/tmpgxo_i92h/images/random contains 5000 images
+<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpx4ylsxc9/images/target contains 8144 images
+/tmp/tmpx4ylsxc9/images/random contains 5000 images
 </pre></div>
 </div>
 </div>
@@ -689,13 +689,13 @@ the time on our validation set).</p>
 </pre></div>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 56s - loss: 0.2188 - accuracy: 0.9243 - val_loss: 0.1368 - val_accuracy: 0.9615
+328/328 - 56s - loss: 0.2243 - accuracy: 0.9248 - val_loss: 0.1480 - val_accuracy: 0.9554
 Epoch 2/3
-328/328 - 52s - loss: 0.1021 - accuracy: 0.9624 - val_loss: 0.1230 - val_accuracy: 0.9588
+328/328 - 53s - loss: 0.0924 - accuracy: 0.9653 - val_loss: 0.1522 - val_accuracy: 0.9596
 Epoch 3/3
-328/328 - 52s - loss: 0.0689 - accuracy: 0.9749 - val_loss: 0.1342 - val_accuracy: 0.9581
+328/328 - 52s - loss: 0.0627 - accuracy: 0.9766 - val_loss: 0.1156 - val_accuracy: 0.9668
 
-&lt;keras.callbacks.History object at 0x7f1b6c658410&gt;
+&lt;keras.callbacks.History object at 0x7fa0ea0be690&gt;
 </pre></div>
 </div>
 </div>
@@ -957,7 +957,7 @@ as intended.</p>
 <p>From here, we could modify the model to read live images from the camera - we have another
 Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
 <a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes  33.393 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes  52.170 seconds)</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-train-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/b52cec46baf4f78d6bcd94cbe269c8a6/micro_train.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">micro_train.py</span></code></a></p>
diff --git a/docs/how_to/work_with_microtvm/sg_execution_times.html b/docs/how_to/work_with_microtvm/sg_execution_times.html
index 5606cfd24..12295974b 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -327,7 +327,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:25.875</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>05:47.774</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 83%" />
@@ -336,19 +336,19 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>04:33.393</p></td>
+<td><p>04:52.170</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:41.659</p></td>
+<td><p>00:43.741</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="micro_aot.html#sphx-glr-how-to-work-with-microtvm-micro-aot-py"><span class="std std-ref">microTVM Host-Driven AoT</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:07.582</p></td>
+<td><p>00:08.399</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:03.238</p></td>
+<td><p>00:03.462</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_relay/sg_execution_times.html b/docs/how_to/work_with_relay/sg_execution_times.html
index 2135c97b7..16288c295 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -327,7 +327,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:42.133</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:40.403</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 84%" />
@@ -336,15 +336,15 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="using_pipeline_executor.html#sphx-glr-how-to-work-with-relay-using-pipeline-executor-py"><span class="std std-ref">Using Pipeline Executor in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_pipeline_executor.py</span></code>)</p></td>
-<td><p>00:30.851</p></td>
+<td><p>00:32.535</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></td>
-<td><p>00:09.860</p></td>
+<td><p>00:06.285</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="build_gcn.html#sphx-glr-how-to-work-with-relay-build-gcn-py"><span class="std std-ref">Building a Graph Convolutional Network</span></a> (<code class="docutils literal notranslate"><span class="pre">build_gcn.py</span></code>)</p></td>
-<td><p>00:01.415</p></td>
+<td><p>00:01.576</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="using_relay_viz.html#sphx-glr-how-to-work-with-relay-using-relay-viz-py"><span class="std std-ref">Use Relay Visualizer to Visualize Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_relay_viz.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/intrin_math.html b/docs/how_to/work_with_schedules/intrin_math.html
index e396886ba..cf2dd9bc6 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -522,7 +522,7 @@ The following example customizes CUDA lowering rule for <code class="code docuti
 <a href="../../reference/api/python/ir.html#tvm.ir.register_intrin_lowering" title="tvm.ir.register_intrin_lowering" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-function"><span class="n">register_intrin_lowering</span></a><span class="p">(</span><span class="s2">&quot;tir.exp&quot;</span><span class="p">,</span> <span class="n">target</span><span class="o">=</span><span class="s2">&quot;cuda&quot;</span><span class="p">,</span> <span class="n">f</span><span class="o">= [...]
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>&lt;function my_cuda_math_rule at 0x7f1af0aaae60&gt;
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>&lt;function my_cuda_math_rule at 0x7fa0d3eeb7a0&gt;
 </pre></div>
 </div>
 <p>Register the rule to TVM with override option to override existing rule.
diff --git a/docs/how_to/work_with_schedules/sg_execution_times.html b/docs/how_to/work_with_schedules/sg_execution_times.html
index 3a1f78818..9862a6ed5 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -327,7 +327,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:04.102</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:04.433</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 83%" />
@@ -336,27 +336,27 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:01.891</p></td>
+<td><p>00:02.042</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="tensorize.html#sphx-glr-how-to-work-with-schedules-tensorize-py"><span class="std std-ref">Use Tensorize to Leverage Hardware Intrinsics</span></a> (<code class="docutils literal notranslate"><span class="pre">tensorize.py</span></code>)</p></td>
-<td><p>00:00.985</p></td>
+<td><p>00:01.084</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="reduction.html#sphx-glr-how-to-work-with-schedules-reduction-py"><span class="std std-ref">Reduction</span></a> (<code class="docutils literal notranslate"><span class="pre">reduction.py</span></code>)</p></td>
-<td><p>00:00.529</p></td>
+<td><p>00:00.564</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="scan.html#sphx-glr-how-to-work-with-schedules-scan-py"><span class="std std-ref">Scan and Recurrent Kernel</span></a> (<code class="docutils literal notranslate"><span class="pre">scan.py</span></code>)</p></td>
-<td><p>00:00.515</p></td>
+<td><p>00:00.555</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="extern_op.html#sphx-glr-how-to-work-with-schedules-extern-op-py"><span class="std std-ref">External Tensor Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">extern_op.py</span></code>)</p></td>
-<td><p>00:00.100</p></td>
+<td><p>00:00.102</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
-<td><p>00:00.041</p></td>
+<td><p>00:00.044</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index bc9370b0e..0c5963bba 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -577,7 +577,7 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
              C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
   buffer_map = {A_1: A, B_1: B, C_1: C}
   preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
-  attr [IterVar(i: int32, (nullptr), &quot;DataPar&quot;, &quot;&quot;)] &quot;pragma_import_llvm&quot; = &quot;; ModuleID = &#39;/tmp/tmp_y9hpy4f/input0.cc&#39;\nsource_filename = \&quot;/tmp/tmp_y9hpy4f/input0.cc\&quot;\ntarget datalayout = \&quot;e-m:e-i64:64-f80:128-n8:16:32:64-S128\&quot;\ntarget triple = \&quot;x86_64-pc-linux-gnu\&quot;\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n  %7 = allo [...]
+  attr [IterVar(i: int32, (nullptr), &quot;DataPar&quot;, &quot;&quot;)] &quot;pragma_import_llvm&quot; = &quot;; ModuleID = &#39;/tmp/tmp3amilt2v/input0.cc&#39;\nsource_filename = \&quot;/tmp/tmp3amilt2v/input0.cc\&quot;\ntarget datalayout = \&quot;e-m:e-i64:64-f80:128-n8:16:32:64-S128\&quot;\ntarget triple = \&quot;x86_64-pc-linux-gnu\&quot;\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n  %7 = allo [...]
   for (i, 0, 1024) {
     for (j.outer: int32, 0, 32) {
       @tir.call_extern(&quot;gemv_update&quot;, @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/install/nnpack.html b/docs/install/nnpack.html
index 3153785d7..aa2238b85 100644
--- a/docs/install/nnpack.html
+++ b/docs/install/nnpack.html
@@ -224,7 +224,17 @@
               <p class="caption" role="heading"><span class="caption-text">Getting Started</span></p>
 <ul class="current">
 <li class="toctree-l1 current"><a class="reference internal" href="index.html">Installing TVM</a><ul class="current">
-<li class="toctree-l2"><a class="reference internal" href="from_source.html">Install from Source</a></li>
+<li class="toctree-l2 current"><a class="reference internal" href="from_source.html">Install from Source</a><ul class="current">
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#developers-get-source-from-github">Developers: Get Source from Github</a></li>
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#build-the-shared-library">Build the Shared Library</a></li>
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#python-package-installation">Python Package Installation</a></li>
+<li class="toctree-l3 current"><a class="reference internal" href="from_source.html#install-contrib-libraries">Install Contrib Libraries</a><ul class="current">
+<li class="toctree-l4 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a></li>
+</ul>
+</li>
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#enable-c-tests">Enable C++ Tests</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="docker.html">Docker Images</a></li>
 <li class="toctree-l2 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a><ul>
 <li class="toctree-l3"><a class="reference internal" href="#conditions">Conditions</a></li>
diff --git a/docs/objects.inv b/docs/objects.inv
index 20878cda3..88a393862 100644
Binary files a/docs/objects.inv and b/docs/objects.inv differ
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index c89d9526e..7d02cc875 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1602,7 +1602,7 @@ history states as starting point to perform Evolutionary Search).</p></li>
 
 <dl class="py class">
 <dt class="sig sig-object py" id="tvm.auto_scheduler.SketchPolicy">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
 <dd><p>The search policy that searches in a hierarchical search space defined by sketches.
 The policy randomly samples programs from the space defined by sketches and use evolutionary
 search to fine-tune them.</p>
@@ -1886,7 +1886,7 @@ Candidates:
 
 <dl class="py function">
 <dt class="sig sig-object py" id="tvm.auto_scheduler.auto_schedule">
-<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
 <dd><p>THIS API IS DEPRECATED.</p>
 <p>Run auto scheduling search for a task.</p>
 <dl class="field-list simple">
diff --git a/docs/reference/api/python/tir.html b/docs/reference/api/python/tir.html
index 600a7fc96..9f5efb7bd 100644
--- a/docs/reference/api/python/tir.html
+++ b/docs/reference/api/python/tir.html
@@ -720,6 +720,18 @@
 <tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.tvm_fill_fragment" title="tvm.tir.tvm_fill_fragment"><code class="xref py py-obj docutils literal notranslate"><span class="pre">tvm_fill_fragment</span></code></a>(fragment, m, n, k, index, ...)</p></td>
 <td><p>TVM intrinsic for tensor core fill_fragment operators</p></td>
 </tr>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.ptx_ldmatrix" title="tvm.tir.ptx_ldmatrix"><code class="xref py py-obj docutils literal notranslate"><span class="pre">ptx_ldmatrix</span></code></a>(dtype, trans, num, type, ...)</p></td>
+<td><p>TVM intrinsic for ptx load matrix from shared memory <a class="reference external" href="https://docs.nvidia.com/cuda/parallel-thread-execution/index.html#warp-level-matrix-instructions-ldmatrix">https://docs.nvidia.com/cuda/parallel-thread-execution/index.html#warp-level-matrix-instructions-ldmatrix</a></p></td>
+</tr>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.ptx_cp_async" title="tvm.tir.ptx_cp_async"><code class="xref py py-obj docutils literal notranslate"><span class="pre">ptx_cp_async</span></code></a>(dtype, shared_ptr, ...)</p></td>
+<td><p>TVM intrinsic for ptx async copy from global to shared memory <a class="reference external" href="https://docs.nvidia.com/cuda/parallel-thread-execution/index.html#data-movement-and-conversion-instructions-cp-async">https://docs.nvidia.com/cuda/parallel-thread-execution/index.html#data-movement-and-conversion-instructions-cp-async</a></p></td>
+</tr>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.ptx_commit_group" title="tvm.tir.ptx_commit_group"><code class="xref py py-obj docutils literal notranslate"><span class="pre">ptx_commit_group</span></code></a>()</p></td>
+<td><p>TVM intrinsic for ptx async copy commit <a class="reference external" href="https://docs.nvidia.com/cuda/parallel-thread-execution/index.html#data-movement-and-conversion-instructions-cp-async-commit-group">https://docs.nvidia.com/cuda/parallel-thread-execution/index.html#data-movement-and-conversion-instructions-cp-async-commit-group</a></p></td>
+</tr>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.ptx_wait_group" title="tvm.tir.ptx_wait_group"><code class="xref py py-obj docutils literal notranslate"><span class="pre">ptx_wait_group</span></code></a>(num)</p></td>
+<td><p>TVM intrinsic for ptx async copy wait <a class="reference external" href="https://docs.nvidia.com/cuda/parallel-thread-execution/index.html#data-movement-and-conversion-instructions-cp-async-wait-group">https://docs.nvidia.com/cuda/parallel-thread-execution/index.html#data-movement-and-conversion-instructions-cp-async-wait-group</a></p></td>
+</tr>
 <tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.vectorlow" title="tvm.tir.vectorlow"><code class="xref py py-obj docutils literal notranslate"><span class="pre">vectorlow</span></code></a>(dtype, vec)</p></td>
 <td><p>Get the low level half of the vector</p></td>
 </tr>
@@ -3544,6 +3556,91 @@ tvm.default_trace_action is used.</p>
 </dl>
 </dd></dl>
 
+<dl class="py function">
+<dt class="sig sig-object py" id="tvm.tir.ptx_ldmatrix">
+<span class="sig-prename descclassname"><span class="pre">tvm.tir.</span></span><span class="sig-name descname"><span class="pre">ptx_ldmatrix</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dtype</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">trans</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">type [...]
+<dd><p>TVM intrinsic for ptx load matrix from shared memory
+<a class="reference external" href="https://docs.nvidia.com/cuda/parallel-thread-execution/index.html#warp-level-matrix-instructions-ldmatrix">https://docs.nvidia.com/cuda/parallel-thread-execution/index.html#warp-level-matrix-instructions-ldmatrix</a></p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>dtype</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.10)"><em>str</em></a>) – The data type of the result.</p></li>
+<li><p><strong>trans</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.10)"><em>bool</em></a>) – The matrix is loaded in column-major format.</p></li>
+<li><p><strong>num</strong> (<a class="reference internal" href="#tvm.tir.IntImm" title="tvm.tir.IntImm"><em>IntImm</em></a>) – The number of matrices.</p></li>
+<li><p><strong>type</strong> (<em>Literal</em><em>[</em><em>&quot;.b16&quot;</em><em>]</em>) – The data type of the matrices.</p></li>
+<li><p><strong>local_ptr</strong> (<a class="reference internal" href="#tvm.tir.Var" title="tvm.tir.Var"><em>Var</em></a>) – The local pointer variable.</p></li>
+<li><p><strong>local_offset</strong> (<em>Expr</em>) – The offset of local pointer.</p></li>
+<li><p><strong>smem_ptr</strong> (<a class="reference internal" href="#tvm.tir.Var" title="tvm.tir.Var"><em>Var</em></a>) – The shared memory pointer variable.</p></li>
+<li><p><strong>smem_offset</strong> (<em>Expr</em>) – The offset of shared memort pointer.</p></li>
+</ul>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p><strong>call</strong> – The call expression.</p>
+</dd>
+<dt class="field-odd">Return type</dt>
+<dd class="field-odd"><p><a class="reference internal" href="ir.html#tvm.ir.PrimExpr" title="tvm.ir.PrimExpr">PrimExpr</a></p>
+</dd>
+</dl>
+</dd></dl>
+
+<dl class="py function">
+<dt class="sig sig-object py" id="tvm.tir.ptx_cp_async">
+<span class="sig-prename descclassname"><span class="pre">tvm.tir.</span></span><span class="sig-name descname"><span class="pre">ptx_cp_async</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dtype</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">shared_ptr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">shared_offset</span></span></em>, <em class="sig-param"><span class="n"><span c [...]
+<dd><p>TVM intrinsic for ptx async copy from global to shared memory
+<a class="reference external" href="https://docs.nvidia.com/cuda/parallel-thread-execution/index.html#data-movement-and-conversion-instructions-cp-async">https://docs.nvidia.com/cuda/parallel-thread-execution/index.html#data-movement-and-conversion-instructions-cp-async</a></p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>dtype</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.10)"><em>str</em></a>) – The data type of the result.</p></li>
+<li><p><strong>shared_ptr</strong> (<a class="reference internal" href="#tvm.tir.Var" title="tvm.tir.Var"><em>Var</em></a>) – The shared memory pointer variable.</p></li>
+<li><p><strong>shared_offset</strong> (<em>Expr</em>) – The offset of shared memory pointer.</p></li>
+<li><p><strong>global_ptr</strong> (<a class="reference internal" href="#tvm.tir.Var" title="tvm.tir.Var"><em>Var</em></a>) – The global memory pointer variable.</p></li>
+<li><p><strong>global_offset</strong> (<em>Expr</em>) – The offset of global memory pointer.</p></li>
+<li><p><strong>bytes</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.10)"><em>int</em></a>) – The data size to copy.</p></li>
+</ul>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p><strong>call</strong> – The call expression.</p>
+</dd>
+<dt class="field-odd">Return type</dt>
+<dd class="field-odd"><p><a class="reference internal" href="ir.html#tvm.ir.PrimExpr" title="tvm.ir.PrimExpr">PrimExpr</a></p>
+</dd>
+</dl>
+</dd></dl>
+
+<dl class="py function">
+<dt class="sig sig-object py" id="tvm.tir.ptx_commit_group">
+<span class="sig-prename descclassname"><span class="pre">tvm.tir.</span></span><span class="sig-name descname"><span class="pre">ptx_commit_group</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#tvm.tir.ptx_commit_group" title="Permalink to this definition">¶</a></dt>
+<dd><p>TVM intrinsic for ptx async copy commit
+<a class="reference external" href="https://docs.nvidia.com/cuda/parallel-thread-execution/index.html#data-movement-and-conversion-instructions-cp-async-commit-group">https://docs.nvidia.com/cuda/parallel-thread-execution/index.html#data-movement-and-conversion-instructions-cp-async-commit-group</a></p>
+<dl class="field-list simple">
+<dt class="field-odd">Returns</dt>
+<dd class="field-odd"><p><strong>call</strong> – The call expression.</p>
+</dd>
+<dt class="field-even">Return type</dt>
+<dd class="field-even"><p><a class="reference internal" href="ir.html#tvm.ir.PrimExpr" title="tvm.ir.PrimExpr">PrimExpr</a></p>
+</dd>
+</dl>
+</dd></dl>
+
+<dl class="py function">
+<dt class="sig sig-object py" id="tvm.tir.ptx_wait_group">
+<span class="sig-prename descclassname"><span class="pre">tvm.tir.</span></span><span class="sig-name descname"><span class="pre">ptx_wait_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#tvm.tir.ptx_wait_group" title="Permalink to this definition">¶</a></dt>
+<dd><p>TVM intrinsic for ptx async copy wait
+<a class="reference external" href="https://docs.nvidia.com/cuda/parallel-thread-execution/index.html#data-movement-and-conversion-instructions-cp-async-wait-group">https://docs.nvidia.com/cuda/parallel-thread-execution/index.html#data-movement-and-conversion-instructions-cp-async-wait-group</a></p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><p><strong>num</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.10)"><em>int</em></a>) – The number of the most recent uncommitted pending cp.async groups to wait.</p>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p><strong>call</strong> – The call expression.</p>
+</dd>
+<dt class="field-odd">Return type</dt>
+<dd class="field-odd"><p><a class="reference internal" href="ir.html#tvm.ir.PrimExpr" title="tvm.ir.PrimExpr">PrimExpr</a></p>
+</dd>
+</dl>
+</dd></dl>
+
 <dl class="py function">
 <dt class="sig sig-object py" id="tvm.tir.vectorlow">
 <span class="sig-prename descclassname"><span class="pre">tvm.tir.</span></span><span class="sig-name descname"><span class="pre">vectorlow</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dtype</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">vec</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#tvm.tir.vectorlow" title="Permalink to this definition">¶</a></dt>
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index 1d67f119b..265f3ae96 100644
--- a/docs/reference/api/typedoc/classes/bytestreamreader.html
+++ b/docs/reference/api/typedoc/classes/bytestreamreader.html
@@ -119,7 +119,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -141,7 +141,7 @@
 					<div class="tsd-signature tsd-kind-icon">bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Uint8Array</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -151,7 +151,7 @@
 					<div class="tsd-signature tsd-kind-icon">offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 0</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -168,7 +168,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">Uint8Array</span></h4>
@@ -185,7 +185,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -202,7 +202,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
diff --git a/docs/reference/api/typedoc/classes/cachedcallstack.html b/docs/reference/api/typedoc/classes/cachedcallstack.html
index 1f6cd81ec..e99d58226 100644
--- a/docs/reference/api/typedoc/classes/cachedcallstack.html
+++ b/docs/reference/api/typedoc/classes/cachedcallstack.html
@@ -144,7 +144,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/memory.ts#L223">memory.ts:223</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/memory.ts#L223">memory.ts:223</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -172,7 +172,7 @@
 					<div class="tsd-signature tsd-kind-icon">temp<wbr>Args<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol">&lt;</span><a href="../interfaces/disposable.html" class="tsd-signature-type">Disposable</a><span class="tsd-signature-symbol">&gt;</span><span class="tsd-signature-symbol"> = []</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/memory.ts#L208">memory.ts:208</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/memory.ts#L208">memory.ts:208</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -194,7 +194,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/memory.ts#L312">memory.ts:312</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/memory.ts#L312">memory.ts:312</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -226,7 +226,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/memory.ts#L284">memory.ts:284</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/memory.ts#L284">memory.ts:284</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -262,7 +262,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/memory.ts#L388">memory.ts:388</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/memory.ts#L388">memory.ts:388</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -300,7 +300,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/memory.ts#L376">memory.ts:376</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/memory.ts#L376">memory.ts:376</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -340,7 +340,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/memory.ts#L267">memory.ts:267</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/memory.ts#L267">memory.ts:267</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -373,7 +373,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/memory.ts#L243">memory.ts:243</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/memory.ts#L243">memory.ts:243</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -390,7 +390,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/memory.ts#L321">memory.ts:321</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/memory.ts#L321">memory.ts:321</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -422,7 +422,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/memory.ts#L252">memory.ts:252</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/memory.ts#L252">memory.ts:252</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -444,7 +444,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/memory.ts#L359">memory.ts:359</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/memory.ts#L359">memory.ts:359</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -470,7 +470,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/memory.ts#L342">memory.ts:342</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/memory.ts#L342">memory.ts:342</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -496,7 +496,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/memory.ts#L350">memory.ts:350</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/memory.ts#L350">memory.ts:350</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -522,7 +522,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/memory.ts#L326">memory.ts:326</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/memory.ts#L326">memory.ts:326</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -548,7 +548,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/memory.ts#L363">memory.ts:363</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/memory.ts#L363">memory.ts:363</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -574,7 +574,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/memory.ts#L346">memory.ts:346</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/memory.ts#L346">memory.ts:346</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -600,7 +600,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/memory.ts#L334">memory.ts:334</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/memory.ts#L334">memory.ts:334</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
diff --git a/docs/reference/api/typedoc/classes/dldatatype.html b/docs/reference/api/typedoc/classes/dldatatype.html
index 8fa93f05a..b721fb9bf 100644
--- a/docs/reference/api/typedoc/classes/dldatatype.html
+++ b/docs/reference/api/typedoc/classes/dldatatype.html
@@ -119,7 +119,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L262">runtime.ts:262</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -147,7 +147,7 @@
 					<div class="tsd-signature tsd-kind-icon">bits<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L260">runtime.ts:260</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -162,7 +162,7 @@
 					<div class="tsd-signature tsd-kind-icon">code<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L258">runtime.ts:258</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -177,7 +177,7 @@
 					<div class="tsd-signature tsd-kind-icon">lanes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L262">runtime.ts:262</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -199,7 +199,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L279">runtime.ts:279</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -216,7 +216,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L270">runtime.ts:270</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">string</span></h4>
diff --git a/docs/reference/api/typedoc/classes/dldevice.html b/docs/reference/api/typedoc/classes/dldevice.html
index 5f7fb55d1..e4e40fceb 100644
--- a/docs/reference/api/typedoc/classes/dldevice.html
+++ b/docs/reference/api/typedoc/classes/dldevice.html
@@ -118,7 +118,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L202">runtime.ts:202</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -146,7 +146,7 @@
 					<div class="tsd-signature tsd-kind-icon">device<wbr>Id<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L200">runtime.ts:200</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -161,7 +161,7 @@
 					<div class="tsd-signature tsd-kind-icon">device<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L198">runtime.ts:198</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -183,7 +183,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L223">runtime.ts:223</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -205,7 +205,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L230">runtime.ts:230</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">string</span></h4>
diff --git a/docs/reference/api/typedoc/classes/environment.html b/docs/reference/api/typedoc/classes/environment.html
index a2a70554d..db47907b3 100644
--- a/docs/reference/api/typedoc/classes/environment.html
+++ b/docs/reference/api/typedoc/classes/environment.html
@@ -125,7 +125,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/environment.ts#L86">environment.ts:86</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/environment.ts#L86">environment.ts:86</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -169,7 +169,7 @@
 					<aside class="tsd-sources">
 						<p>Implementation of <a href="../interfaces/libraryprovider.html">LibraryProvider</a>.<a href="../interfaces/libraryprovider.html#imports">imports</a></p>
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/environment.ts#L70">environment.ts:70</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/environment.ts#L70">environment.ts:70</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -179,7 +179,7 @@
 					<div class="tsd-signature tsd-kind-icon">logger<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>msg<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&gt; </span><span class="tsd-signature-type">void</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/environment.ts#L69">environment.ts:69</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/environment.ts#L69">environment.ts:69</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-type-declaration">
@@ -210,7 +210,7 @@
 					<div class="tsd-signature tsd-kind-icon">packedCFunc<wbr>Table<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol">&lt;</span><span class="tsd-signature-type">ctypes.FTVMWasmPackedCFunc</span><span class="tsd-signature-symbol"> | </span><span class="tsd-signature-type">undefined</span><span class="tsd-signature-symbol">&gt;</span><span class="tsd-signature-symbol"> = [undefined,]</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/environment.ts#L78">environment.ts:78</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/environment.ts#L78">environment.ts:78</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -228,7 +228,7 @@
 					<div class="tsd-signature tsd-kind-icon">packedCFunc<wbr>Table<wbr>Free<wbr>Id<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol">&lt;</span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">&gt;</span><span class="tsd-signature-symbol"> = []</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/environment.ts#L84">environment.ts:84</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/environment.ts#L84">environment.ts:84</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -250,7 +250,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/environment.ts#L105">environment.ts:105</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/environment.ts#L105">environment.ts:105</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/ffilibrary.html b/docs/reference/api/typedoc/classes/ffilibrary.html
index 96b26141d..0b7f5d44e 100644
--- a/docs/reference/api/typedoc/classes/ffilibrary.html
+++ b/docs/reference/api/typedoc/classes/ffilibrary.html
@@ -131,7 +131,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L49">runtime.ts:49</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -156,7 +156,7 @@
 					<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol">&lt;</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">&gt;</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L46">runtime.ts:46</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -166,7 +166,7 @@
 					<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L45">runtime.ts:45</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -176,7 +176,7 @@
 					<div class="tsd-signature tsd-kind-icon">wasm32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">boolean</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L44">runtime.ts:44</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -186,7 +186,7 @@
 					<div class="tsd-signature tsd-kind-icon">webGPUContext<span class="tsd-signature-symbol">:</span> <a href="webgpucontext.html" class="tsd-signature-type">WebGPUContext</a></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L47">runtime.ts:47</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -203,7 +203,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L76">runtime.ts:76</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -226,7 +226,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L66">runtime.ts:66</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -243,7 +243,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L84">runtime.ts:84</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-returns-title">Returns <a href="cachedcallstack.html" class="tsd-signature-type">CachedCallStack</a></h4>
@@ -260,7 +260,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L95">runtime.ts:95</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -283,7 +283,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L72">runtime.ts:72</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
diff --git a/docs/reference/api/typedoc/classes/graphexecutor.html b/docs/reference/api/typedoc/classes/graphexecutor.html
index 3f8171780..11aeb74ff 100644
--- a/docs/reference/api/typedoc/classes/graphexecutor.html
+++ b/docs/reference/api/typedoc/classes/graphexecutor.html
@@ -130,7 +130,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L583">runtime.ts:583</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -162,7 +162,7 @@
 					<div class="tsd-signature tsd-kind-icon">module<span class="tsd-signature-symbol">:</span> <a href="module.html" class="tsd-signature-type">Module</a></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L579">runtime.ts:579</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -179,7 +179,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L654">runtime.ts:654</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -224,7 +224,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L597">runtime.ts:597</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -241,7 +241,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L631">runtime.ts:631</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -279,7 +279,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L644">runtime.ts:644</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -310,7 +310,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L621">runtime.ts:621</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -332,7 +332,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L609">runtime.ts:609</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/instance.html b/docs/reference/api/typedoc/classes/instance.html
index a09d6f73e..3f35da53d 100644
--- a/docs/reference/api/typedoc/classes/instance.html
+++ b/docs/reference/api/typedoc/classes/instance.html
@@ -139,7 +139,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L692">runtime.ts:692</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -202,7 +202,7 @@
 					<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol">&lt;</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">&gt;</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L684">runtime.ts:684</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -212,7 +212,7 @@
 					<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L683">runtime.ts:683</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -229,7 +229,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L932">runtime.ts:932</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -260,7 +260,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L994">runtime.ts:994</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -303,7 +303,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L924">runtime.ts:924</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -341,7 +341,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L732">runtime.ts:732</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -358,7 +358,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L952">runtime.ts:952</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -402,7 +402,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L816">runtime.ts:816</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -434,7 +434,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -465,7 +465,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L846">runtime.ts:846</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -497,7 +497,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L750">runtime.ts:750</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -520,7 +520,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -568,7 +568,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L789">runtime.ts:789</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -608,7 +608,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L914">runtime.ts:914</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -646,7 +646,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -698,7 +698,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L740">runtime.ts:740</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -722,7 +722,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L868">runtime.ts:868</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -754,7 +754,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L857">runtime.ts:857</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -786,7 +786,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L940">runtime.ts:940</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/memory.html b/docs/reference/api/typedoc/classes/memory.html
index 4ef0edae5..0afec303b 100644
--- a/docs/reference/api/typedoc/classes/memory.html
+++ b/docs/reference/api/typedoc/classes/memory.html
@@ -130,7 +130,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/memory.ts#L40">memory.ts:40</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/memory.ts#L40">memory.ts:40</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -152,7 +152,7 @@
 					<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Memory</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/memory.ts#L32">memory.ts:32</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/memory.ts#L32">memory.ts:32</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -162,7 +162,7 @@
 					<div class="tsd-signature tsd-kind-icon">wasm32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">boolean</span><span class="tsd-signature-symbol"> = true</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/memory.ts#L33">memory.ts:33</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/memory.ts#L33">memory.ts:33</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -179,7 +179,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/memory.ts#L154">memory.ts:154</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/memory.ts#L154">memory.ts:154</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -210,7 +210,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/memory.ts#L90">memory.ts:90</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/memory.ts#L90">memory.ts:90</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -233,7 +233,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/memory.ts#L97">memory.ts:97</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/memory.ts#L97">memory.ts:97</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -256,7 +256,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/memory.ts#L74">memory.ts:74</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/memory.ts#L74">memory.ts:74</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -279,7 +279,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/memory.ts#L81">memory.ts:81</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/memory.ts#L81">memory.ts:81</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -302,7 +302,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/memory.ts#L104">memory.ts:104</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/memory.ts#L104">memory.ts:104</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -325,7 +325,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/memory.ts#L132">memory.ts:132</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/memory.ts#L132">memory.ts:132</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -362,7 +362,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/memory.ts#L145">memory.ts:145</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/memory.ts#L145">memory.ts:145</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -393,7 +393,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/memory.ts#L60">memory.ts:60</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/memory.ts#L60">memory.ts:60</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -416,7 +416,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/memory.ts#L67">memory.ts:67</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/memory.ts#L67">memory.ts:67</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -439,7 +439,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/memory.ts#L53">memory.ts:53</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/memory.ts#L53">memory.ts:53</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -462,7 +462,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/memory.ts#L114">memory.ts:114</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/memory.ts#L114">memory.ts:114</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -485,7 +485,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/memory.ts#L124">memory.ts:124</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/memory.ts#L124">memory.ts:124</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -502,7 +502,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/memory.ts#L175">memory.ts:175</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/memory.ts#L175">memory.ts:175</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/module.html b/docs/reference/api/typedoc/classes/module.html
index 197b9b15d..e41e562f4 100644
--- a/docs/reference/api/typedoc/classes/module.html
+++ b/docs/reference/api/typedoc/classes/module.html
@@ -124,7 +124,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L504">runtime.ts:504</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -170,7 +170,7 @@
 					<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L502">runtime.ts:502</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -187,7 +187,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L516">runtime.ts:516</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -204,7 +204,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L530">runtime.ts:530</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -236,7 +236,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L561">runtime.ts:561</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/ndarray.html b/docs/reference/api/typedoc/classes/ndarray.html
index 6fa98a7d4..2c0e88ed5 100644
--- a/docs/reference/api/typedoc/classes/ndarray.html
+++ b/docs/reference/api/typedoc/classes/ndarray.html
@@ -130,7 +130,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L304">runtime.ts:304</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -158,7 +158,7 @@
 					<div class="tsd-signature tsd-kind-icon">device<span class="tsd-signature-symbol">:</span> <a href="dldevice.html" class="tsd-signature-type">DLDevice</a></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L297">runtime.ts:297</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -173,7 +173,7 @@
 					<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L293">runtime.ts:293</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -188,7 +188,7 @@
 					<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L289">runtime.ts:289</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -203,7 +203,7 @@
 					<div class="tsd-signature tsd-kind-icon">ndim<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L291">runtime.ts:291</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -218,7 +218,7 @@
 					<div class="tsd-signature tsd-kind-icon">shape<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol">&lt;</span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">&gt;</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L295">runtime.ts:295</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -240,7 +240,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L370">runtime.ts:370</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -273,7 +273,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L414">runtime.ts:414</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -305,7 +305,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L355">runtime.ts:355</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -322,7 +322,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L474">runtime.ts:474</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -346,7 +346,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L443">runtime.ts:443</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/packedfunccell.html b/docs/reference/api/typedoc/classes/packedfunccell.html
index e05ba4059..e8e0036be 100644
--- a/docs/reference/api/typedoc/classes/packedfunccell.html
+++ b/docs/reference/api/typedoc/classes/packedfunccell.html
@@ -122,7 +122,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L158">runtime.ts:158</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -147,7 +147,7 @@
 					<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L157">runtime.ts:157</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -164,7 +164,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L165">runtime.ts:165</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
diff --git a/docs/reference/api/typedoc/classes/rpcserver.html b/docs/reference/api/typedoc/classes/rpcserver.html
index 8ec4ca8ae..dc4b8e5d9 100644
--- a/docs/reference/api/typedoc/classes/rpcserver.html
+++ b/docs/reference/api/typedoc/classes/rpcserver.html
@@ -115,7 +115,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -176,7 +176,7 @@
 					<div class="tsd-signature tsd-kind-icon">get<wbr>Imports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&gt; </span><span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol">&lt;</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">unknown</span><span class="tsd-signat [...]
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-type-declaration">
@@ -201,7 +201,7 @@
 					<div class="tsd-signature tsd-kind-icon">key<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -211,7 +211,7 @@
 					<div class="tsd-signature tsd-kind-icon">logger<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>msg<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&gt; </span><span class="tsd-signature-type">void</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-type-declaration">
@@ -242,7 +242,7 @@
 					<div class="tsd-signature tsd-kind-icon">socket<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">WebSocket</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -252,7 +252,7 @@
 					<div class="tsd-signature tsd-kind-icon">state<span class="tsd-signature-symbol">:</span> <a href="../enums/rpcserverstate.html" class="tsd-signature-type">RPCServerState</a><span class="tsd-signature-symbol"> = RPCServerState.InitHeader</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -262,7 +262,7 @@
 					<div class="tsd-signature tsd-kind-icon">url<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
 						</ul>
 					</aside>
 				</section>
diff --git a/docs/reference/api/typedoc/classes/scalar.html b/docs/reference/api/typedoc/classes/scalar.html
index 192646832..803a9d805 100644
--- a/docs/reference/api/typedoc/classes/scalar.html
+++ b/docs/reference/api/typedoc/classes/scalar.html
@@ -112,7 +112,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L145">runtime.ts:145</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -137,7 +137,7 @@
 					<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L145">runtime.ts:145</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -152,7 +152,7 @@
 					<div class="tsd-signature tsd-kind-icon">value<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L143">runtime.ts:143</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/webgpucontext.html b/docs/reference/api/typedoc/classes/webgpucontext.html
index ed5affd3b..bc73763f5 100644
--- a/docs/reference/api/typedoc/classes/webgpucontext.html
+++ b/docs/reference/api/typedoc/classes/webgpucontext.html
@@ -120,7 +120,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -145,7 +145,7 @@
 					<div class="tsd-signature tsd-kind-icon">device<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">GPUDevice</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -155,7 +155,7 @@
 					<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -172,7 +172,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -209,7 +209,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/enums/argtypecode.html b/docs/reference/api/typedoc/enums/argtypecode.html
index 20b463454..f85df5022 100644
--- a/docs/reference/api/typedoc/enums/argtypecode.html
+++ b/docs/reference/api/typedoc/enums/argtypecode.html
@@ -106,7 +106,7 @@
 					<div class="tsd-signature tsd-kind-icon">DLDevice<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 6</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -116,7 +116,7 @@
 					<div class="tsd-signature tsd-kind-icon">Float<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -126,7 +126,7 @@
 					<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -136,7 +136,7 @@
 					<div class="tsd-signature tsd-kind-icon">Null<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -146,7 +146,7 @@
 					<div class="tsd-signature tsd-kind-icon">TVMBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 12</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -156,7 +156,7 @@
 					<div class="tsd-signature tsd-kind-icon">TVMDLTensor<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 7</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -166,7 +166,7 @@
 					<div class="tsd-signature tsd-kind-icon">TVMData<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 5</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -176,7 +176,7 @@
 					<div class="tsd-signature tsd-kind-icon">TVMModule<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 9</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -186,7 +186,7 @@
 					<div class="tsd-signature tsd-kind-icon">TVMNDArray<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 13</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -196,7 +196,7 @@
 					<div class="tsd-signature tsd-kind-icon">TVMObject<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -206,7 +206,7 @@
 					<div class="tsd-signature tsd-kind-icon">TVMObjectRValue<wbr>Ref<wbr>Arg<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 14</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -216,7 +216,7 @@
 					<div class="tsd-signature tsd-kind-icon">TVMOpaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -226,7 +226,7 @@
 					<div class="tsd-signature tsd-kind-icon">TVMPacked<wbr>Func<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 10</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -236,7 +236,7 @@
 					<div class="tsd-signature tsd-kind-icon">TVMStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 11</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -246,7 +246,7 @@
 					<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
 						</ul>
 					</aside>
 				</section>
diff --git a/docs/reference/api/typedoc/enums/aynccallbackcode.html b/docs/reference/api/typedoc/enums/aynccallbackcode.html
index 1305de3de..a66c967ce 100644
--- a/docs/reference/api/typedoc/enums/aynccallbackcode.html
+++ b/docs/reference/api/typedoc/enums/aynccallbackcode.html
@@ -93,7 +93,7 @@
 					<div class="tsd-signature tsd-kind-icon">k<wbr>Exception<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 5</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L676">runtime.ts:676</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -103,7 +103,7 @@
 					<div class="tsd-signature tsd-kind-icon">k<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L675">runtime.ts:675</a></li>
 						</ul>
 					</aside>
 				</section>
diff --git a/docs/reference/api/typedoc/enums/dldatatypecode.html b/docs/reference/api/typedoc/enums/dldatatypecode.html
index baa51334f..3d5766bb9 100644
--- a/docs/reference/api/typedoc/enums/dldatatypecode.html
+++ b/docs/reference/api/typedoc/enums/dldatatypecode.html
@@ -95,7 +95,7 @@
 					<div class="tsd-signature tsd-kind-icon">Float<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L242">runtime.ts:242</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -105,7 +105,7 @@
 					<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L240">runtime.ts:240</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -115,7 +115,7 @@
 					<div class="tsd-signature tsd-kind-icon">Opaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L243">runtime.ts:243</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -125,7 +125,7 @@
 					<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L241">runtime.ts:241</a></li>
 						</ul>
 					</aside>
 				</section>
diff --git a/docs/reference/api/typedoc/enums/rpcserverstate.html b/docs/reference/api/typedoc/enums/rpcserverstate.html
index 2f9e86358..de1d9aca8 100644
--- a/docs/reference/api/typedoc/enums/rpcserverstate.html
+++ b/docs/reference/api/typedoc/enums/rpcserverstate.html
@@ -90,7 +90,7 @@
 					<div class="tsd-signature tsd-kind-icon">Init<wbr>Header<span class="tsd-signature-symbol">:</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -100,7 +100,7 @@
 					<div class="tsd-signature tsd-kind-icon">Init<wbr>Header<wbr>Key<span class="tsd-signature-symbol">:</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -110,7 +110,7 @@
 					<div class="tsd-signature tsd-kind-icon">Init<wbr>Server<span class="tsd-signature-symbol">:</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -120,7 +120,7 @@
 					<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Body<span class="tsd-signature-symbol">:</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -130,7 +130,7 @@
 					<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Header<span class="tsd-signature-symbol">:</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -140,7 +140,7 @@
 					<div class="tsd-signature tsd-kind-icon">Wait<wbr>For<wbr>Callback<span class="tsd-signature-symbol">:</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
 						</ul>
 					</aside>
 				</section>
diff --git a/docs/reference/api/typedoc/enums/sizeof.html b/docs/reference/api/typedoc/enums/sizeof.html
index bd5ccdff7..47d5bfd23 100644
--- a/docs/reference/api/typedoc/enums/sizeof.html
+++ b/docs/reference/api/typedoc/enums/sizeof.html
@@ -100,7 +100,7 @@
 					<div class="tsd-signature tsd-kind-icon">DLData<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = I32</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -110,7 +110,7 @@
 					<div class="tsd-signature tsd-kind-icon">DLDevice<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = I32 + I32</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -120,7 +120,7 @@
 					<div class="tsd-signature tsd-kind-icon">F32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -130,7 +130,7 @@
 					<div class="tsd-signature tsd-kind-icon">F64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -140,7 +140,7 @@
 					<div class="tsd-signature tsd-kind-icon">I32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -150,7 +150,7 @@
 					<div class="tsd-signature tsd-kind-icon">I64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -160,7 +160,7 @@
 					<div class="tsd-signature tsd-kind-icon">TVMValue<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -170,7 +170,7 @@
 					<div class="tsd-signature tsd-kind-icon">U16<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -180,7 +180,7 @@
 					<div class="tsd-signature tsd-kind-icon">U8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
 						</ul>
 					</aside>
 				</section>
diff --git a/docs/reference/api/typedoc/index.html b/docs/reference/api/typedoc/index.html
index e707a8bf2..cd019cbba 100644
--- a/docs/reference/api/typedoc/index.html
+++ b/docs/reference/api/typedoc/index.html
@@ -174,7 +174,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Alloc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>shape<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, ndim<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeCode<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeBits<span class="tsd [...]
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>Bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">num [...]
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -282,7 +282,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>To<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>from<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, to<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-sig [...]
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -326,7 +326,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>ToBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</sp [...]
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -370,7 +370,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&gt; </span><span class="tsd-signature-type">number</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -406,7 +406,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMBackend<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number< [...]
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -458,7 +458,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMCFunc<wbr>Set<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ret<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signa [...]
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -506,7 +506,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMCb<wbr>Arg<wbr>ToReturn<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, code<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&gt; </span><span c [...]
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -545,7 +545,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Call<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-t [...]
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -601,7 +601,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&gt; </span><span class="tsd-signature-type">number</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -637,7 +637,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Get<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&gt; </span><span cla [...]
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -676,7 +676,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>List<wbr>Global<wbr>Names<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>outSize<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, outArray<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -715,7 +715,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Register<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, f<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, override<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</spa [...]
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -758,7 +758,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMGet<wbr>Last<wbr>Error<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&gt; </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -788,7 +788,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&gt; </span><span class="tsd-signature-type">number</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -824,7 +824,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Get<wbr>Function<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, funcName<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, queryImports<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">numbe [...]
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -872,7 +872,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Import<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, dep<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&gt; </span><span class="tsd-si [...]
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -912,7 +912,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMSynchronize<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>deviceType<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, deviceId<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signatur [...]
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -954,7 +954,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Alloc<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>size<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&gt; </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -990,7 +990,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Free<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ptr<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&gt; </span><span class="tsd-signature-type">void</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -1026,7 +1026,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Func<wbr>Create<wbr>FromCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resource<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -1066,7 +1066,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>args<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, [...]
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -1118,7 +1118,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<wbr>Finalizer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resourceHandle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&gt; </span><span class="tsd-signature-type">void</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -1154,7 +1154,7 @@
 					<div class="tsd-signature tsd-kind-icon">GPUPointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -1169,7 +1169,7 @@
 					<div class="tsd-signature tsd-kind-icon">Packed<wbr>Func<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">...</span>args<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&gt; </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol"> &amp; </span><a href="interfaces/disp [...]
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L36">runtime.ts:36</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -1184,7 +1184,7 @@
 					<div class="tsd-signature tsd-kind-icon">Pointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -1199,7 +1199,7 @@
 					<div class="tsd-signature tsd-kind-icon">Ptr<wbr>Offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -1217,7 +1217,7 @@
 					<div class="tsd-signature tsd-kind-icon">RPC_<wbr>MAGIC<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">1045105</span><span class="tsd-signature-symbol"> = 1045105</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -1239,7 +1239,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/support.ts#L25">support.ts:25</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/support.ts#L25">support.ts:25</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -1271,7 +1271,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/support.ts#L39">support.ts:39</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/support.ts#L39">support.ts:39</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -1300,7 +1300,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/support.ts#L52">support.ts:52</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/support.ts#L52">support.ts:52</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -1337,7 +1337,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/compact.ts#L38">compact.ts:38</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/compact.ts#L38">compact.ts:38</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -1368,7 +1368,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -1390,7 +1390,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/environment.ts#L32">environment.ts:32</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/environment.ts#L32">environment.ts:32</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -1421,7 +1421,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/compact.ts#L24">compact.ts:24</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/compact.ts#L24">compact.ts:24</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -1443,7 +1443,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -1508,7 +1508,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/support.ts#L62">support.ts:62</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/support.ts#L62">support.ts:62</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -1530,7 +1530,7 @@
 					<div class="tsd-signature tsd-kind-icon">DLData<wbr>Type<wbr>Code<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/3224817d0/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/4f431c87c/web/src/runtime.ts#L246">runtime.ts:246</a></li>
 						</ul>
... 990 lines suppressed ...