You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by tq...@apache.org on 2022/12/07 18:49:33 UTC

[tvm-site] branch asf-site updated: deploying docs (apache/tvm@f674e12d1a20c817d643e47f35cfc69733326092)

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 1fdadb15de deploying docs (apache/tvm@f674e12d1a20c817d643e47f35cfc69733326092)
1fdadb15de is described below

commit 1fdadb15dea332623e0bde15280768b32f71fea7
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Wed Dec 7 18:49:25 2022 +0000

    deploying docs (apache/tvm@f674e12d1a20c817d643e47f35cfc69733326092)
---
 docs/_images/sphx_glr_micro_train_001.png          |  Bin 335230 -> 324292 bytes
 docs/_images/sphx_glr_micro_train_thumb.png        |  Bin 23974 -> 23851 bytes
 .../how_to/compile_models/from_darknet.rst.txt     |    2 +-
 .../how_to/compile_models/from_keras.rst.txt       |    2 +-
 .../how_to/compile_models/from_mxnet.rst.txt       |    2 +-
 .../how_to/compile_models/from_oneflow.rst.txt     |    2 +-
 .../how_to/compile_models/from_pytorch.rst.txt     |    2 +-
 .../how_to/compile_models/from_tensorflow.rst.txt  |    2 +-
 .../compile_models/sg_execution_times.rst.txt      |   22 +-
 .../deploy_models/deploy_model_on_adreno.rst.txt   |    2 +-
 .../deploy_models/deploy_model_on_android.rst.txt  |    2 +-
 .../deploy_object_detection_pytorch.rst.txt        |    4 +-
 .../deploy_models/deploy_prequantized.rst.txt      |    6 +-
 .../deploy_prequantized_tflite.rst.txt             |    4 +-
 .../how_to/deploy_models/deploy_quantized.rst.txt  |    2 +-
 .../deploy_models/deploy_ssd_gluoncv.rst.txt       |    4 +-
 .../deploy_models/sg_execution_times.rst.txt       |   20 +-
 .../extend_tvm/bring_your_own_datatypes.rst.txt    |    2 +-
 .../how_to/extend_tvm/sg_execution_times.rst.txt   |    8 +-
 .../how_to/extend_tvm/use_pass_instrument.rst.txt  |   16 +-
 .../optimize_operators/opt_conv_cuda.rst.txt       |    2 +-
 .../optimize_operators/opt_conv_tensorcore.rst.txt |    2 +-
 .../how_to/optimize_operators/opt_gemm.rst.txt     |   16 +-
 .../optimize_operators/sg_execution_times.rst.txt  |    8 +-
 .../sg_execution_times.rst.txt                     |   14 +-
 .../tune_conv2d_layer_cuda.rst.txt                 | 2450 +++++++++++++-------
 .../tune_network_cuda.rst.txt                      |    4 +-
 .../tune_network_x86.rst.txt                       |    4 +-
 .../tune_sparse_x86.rst.txt                        |  134 +-
 .../tune_with_autotvm/sg_execution_times.rst.txt   |    4 +-
 .../tune_with_autotvm/tune_conv2d_cuda.rst.txt     |  452 +++-
 .../work_with_microtvm/micro_autotune.rst.txt      |   16 +-
 .../work_with_microtvm/micro_pytorch.rst.txt       |    4 +-
 .../how_to/work_with_microtvm/micro_train.rst.txt  |   18 +-
 .../work_with_microtvm/sg_execution_times.rst.txt  |   12 +-
 .../work_with_relay/sg_execution_times.rst.txt     |    8 +-
 .../how_to/work_with_schedules/intrin_math.rst.txt |    2 +-
 .../work_with_schedules/sg_execution_times.rst.txt |   12 +-
 .../how_to/work_with_schedules/tensorize.rst.txt   |    2 +-
 .../tutorials/autotvm/sg_execution_times.rst.txt   |    6 +-
 .../frontend/deploy_classification.rst.txt         |    2 +-
 .../tutorials/frontend/deploy_detection.rst.txt    |    2 +-
 .../tutorials/frontend/sg_execution_times.rst.txt  |    6 +-
 .../tutorials/optimize/sg_execution_times.rst.txt  |    6 +-
 .../topic/vta/tutorials/sg_execution_times.rst.txt |    6 +-
 .../tutorial/auto_scheduler_matmul_x86.rst.txt     |    6 +-
 docs/_sources/tutorial/autotvm_matmul_x86.rst.txt  |   20 +-
 docs/_sources/tutorial/autotvm_relay_x86.rst.txt   |   62 +-
 .../tutorial/cross_compilation_and_rpc.rst.txt     |    2 +-
 docs/_sources/tutorial/intro_topi.rst.txt          |    2 +-
 docs/_sources/tutorial/sg_execution_times.rst.txt  |   22 +-
 .../tutorial/tensor_expr_get_started.rst.txt       |   44 +-
 docs/commit_hash                                   |    2 +-
 docs/how_to/compile_models/from_darknet.html       |    2 +-
 docs/how_to/compile_models/from_keras.html         |    2 +-
 docs/how_to/compile_models/from_mxnet.html         |    2 +-
 docs/how_to/compile_models/from_oneflow.html       |   14 +-
 docs/how_to/compile_models/from_pytorch.html       |    9 +-
 docs/how_to/compile_models/from_tensorflow.html    |    2 +-
 docs/how_to/compile_models/sg_execution_times.html |   22 +-
 .../deploy_models/deploy_model_on_adreno.html      |    2 +-
 .../deploy_models/deploy_model_on_android.html     |    2 +-
 .../deploy_object_detection_pytorch.html           |   45 +-
 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  |   37 +-
 docs/how_to/deploy_models/sg_execution_times.html  |   24 +-
 .../extend_tvm/bring_your_own_datatypes.html       |    2 +-
 docs/how_to/extend_tvm/sg_execution_times.html     |    8 +-
 docs/how_to/extend_tvm/use_pass_instrument.html    |   16 +-
 docs/how_to/optimize_operators/opt_conv_cuda.html  |    2 +-
 .../optimize_operators/opt_conv_tensorcore.html    |    2 +-
 docs/how_to/optimize_operators/opt_gemm.html       |   16 +-
 .../optimize_operators/sg_execution_times.html     |    8 +-
 .../sg_execution_times.html                        |   14 +-
 .../tune_conv2d_layer_cuda.html                    | 2450 +++++++++++++-------
 .../tune_with_autoscheduler/tune_network_cuda.html |    4 +-
 .../tune_with_autoscheduler/tune_network_x86.html  |    4 +-
 .../tune_with_autoscheduler/tune_sparse_x86.html   |  134 +-
 .../tune_with_autotvm/sg_execution_times.html      |    4 +-
 .../how_to/tune_with_autotvm/tune_conv2d_cuda.html |  448 +++-
 docs/how_to/work_with_microtvm/micro_autotune.html |   16 +-
 docs/how_to/work_with_microtvm/micro_pytorch.html  |    5 +-
 docs/how_to/work_with_microtvm/micro_train.html    |   16 +-
 .../work_with_microtvm/sg_execution_times.html     |   12 +-
 .../how_to/work_with_relay/sg_execution_times.html |    8 +-
 docs/how_to/work_with_schedules/intrin_math.html   |    2 +-
 .../work_with_schedules/sg_execution_times.html    |   12 +-
 docs/how_to/work_with_schedules/tensorize.html     |    2 +-
 docs/install/nnpack.html                           |   12 +-
 docs/reference/api/python/auto_scheduler.html      |    4 +-
 .../api/typedoc/classes/bytestreamreader.html      |   12 +-
 .../api/typedoc/classes/cachedcallstack.html       |   34 +-
 docs/reference/api/typedoc/classes/dldatatype.html |   12 +-
 docs/reference/api/typedoc/classes/dldevice.html   |   10 +-
 .../reference/api/typedoc/classes/environment.html |   12 +-
 docs/reference/api/typedoc/classes/ffilibrary.html |   20 +-
 .../api/typedoc/classes/graphexecutor.html         |   16 +-
 docs/reference/api/typedoc/classes/instance.html   |   40 +-
 docs/reference/api/typedoc/classes/memory.html     |   34 +-
 docs/reference/api/typedoc/classes/module.html     |   10 +-
 docs/reference/api/typedoc/classes/ndarray.html    |   22 +-
 .../api/typedoc/classes/packedfunccell.html        |    6 +-
 docs/reference/api/typedoc/classes/rpcserver.html  |   14 +-
 docs/reference/api/typedoc/classes/scalar.html     |    6 +-
 .../api/typedoc/classes/webgpucontext.html         |   12 +-
 docs/reference/api/typedoc/enums/argtypecode.html  |   30 +-
 .../api/typedoc/enums/aynccallbackcode.html        |    4 +-
 .../api/typedoc/enums/dldatatypecode.html          |    8 +-
 .../api/typedoc/enums/rpcserverstate.html          |   12 +-
 docs/reference/api/typedoc/enums/sizeof.html       |   18 +-
 docs/reference/api/typedoc/index.html              |  112 +-
 .../api/typedoc/interfaces/disposable.html         |    2 +-
 .../api/typedoc/interfaces/functioninfo.html       |    6 +-
 .../api/typedoc/interfaces/libraryprovider.html    |    4 +-
 docs/searchindex.js                                |    2 +-
 .../vta/tutorials/autotvm/sg_execution_times.html  |    6 +-
 .../tutorials/frontend/deploy_classification.html  |    2 +-
 .../vta/tutorials/frontend/deploy_detection.html   |    2 +-
 .../vta/tutorials/frontend/sg_execution_times.html |    6 +-
 .../vta/tutorials/optimize/sg_execution_times.html |    6 +-
 docs/topic/vta/tutorials/sg_execution_times.html   |    6 +-
 docs/tutorial/auto_scheduler_matmul_x86.html       |    4 +-
 docs/tutorial/autotvm_matmul_x86.html              |   20 +-
 docs/tutorial/autotvm_relay_x86.html               |  278 ++-
 docs/tutorial/cross_compilation_and_rpc.html       |    2 +-
 docs/tutorial/intro_topi.html                      |    2 +-
 docs/tutorial/sg_execution_times.html              |   22 +-
 docs/tutorial/tensor_expr_get_started.html         |   44 +-
 130 files changed, 4847 insertions(+), 2845 deletions(-)

diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index 4730ebaecb..fd04aec899 100644
Binary files a/docs/_images/sphx_glr_micro_train_001.png and b/docs/_images/sphx_glr_micro_train_001.png differ
diff --git a/docs/_images/sphx_glr_micro_train_thumb.png b/docs/_images/sphx_glr_micro_train_thumb.png
index 4f63c99e35..176d23232e 100644
Binary files a/docs/_images/sphx_glr_micro_train_thumb.png and b/docs/_images/sphx_glr_micro_train_thumb.png differ
diff --git a/docs/_sources/how_to/compile_models/from_darknet.rst.txt b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
index d7d897bbb3..fe22cc5f8d 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -315,7 +315,7 @@ The process is no different from other examples.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  15.301 seconds)
+   **Total running time of the script:** ( 1 minutes  13.173 seconds)
 
 
 .. _sphx_glr_download_how_to_compile_models_from_darknet.py:
diff --git a/docs/_sources/how_to/compile_models/from_keras.rst.txt b/docs/_sources/how_to/compile_models/from_keras.rst.txt
index 5b49d2477a..30629a6d70 100644
--- a/docs/_sources/how_to/compile_models/from_keras.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_keras.rst.txt
@@ -228,7 +228,7 @@ Look up prediction top 1 index in 1000 class synset.
  .. code-block:: none
 
     Relay top-1 id: 285, class name: Egyptian cat
-
    1/1 [==============================] - ETA: 0s
    1/1 [==============================] - 1s 998ms/step
+
    1/1 [==============================] - ETA: 0s
    1/1 [==============================] - 1s 1s/step
     Keras top-1 id: 285, class name: Egyptian cat
 
 
diff --git a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
index ebd2951128..0e1e1791b7 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.zipbd0bd19d-9e87-4c7d-bad5-36e7261a434b from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+    Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipffd83e02-4558-44ce-b694-b4db2dfdde8f 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 88acae4811..9653fd5c64 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -116,7 +116,7 @@ Load a pretrained OneFlow model and save model
  .. code-block:: none
 
     Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
      0%|          | 0.00/41.5M [00:00<?, ?B/s]
     15%|#5        | 6.33M/41.5M [00:00<00:01, 32.8MB/s]
     23%|##2       | 9.46M/41.5M [00:00<00:01, 29.6MB/s]
     39%|###8      | 16.0M/41.5M [00:00<00:00, 34.4MB/s]
     58%|#####7    | 24.0M/41.5M [00:00<00:00, 40.3MB/s]
     77%|#######7  | 32.0M/41.5M [00:00<00:00, 49.3MB/s]
     96%|#########6| 40.0M/41.5M [00:00<00:00, 56.1MB/s]
    100%|##########| 41.5M/41.5M [00:00<00:00, 47.8MB/s]
+
      0%|          | 0.00/41.5M [00:00<?, ?B/s]
     15%|#5        | 6.33M/41.5M [00:00<00:01, 35.2MB/s]
     27%|##6       | 11.1M/41.5M [00:00<00:00, 41.7MB/s]
     39%|###8      | 16.0M/41.5M [00:00<00:00, 35.0MB/s]
     63%|######3   | 26.2M/41.5M [00:00<00:00, 56.3MB/s]
     78%|#######8  | 32.4M/41.5M [00:00<00:00, 56.2MB/s]
     92%|#########2| 38.3M/41.5M [00:00<00:00, 57.0MB/s]
    100%|##########| 41.5M/41.5M [00:00<00:00, 49.2MB/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 0fe7dafce5..7410ad3e1d 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -98,7 +98,7 @@ Load a pretrained PyTorch model
     /venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=ResNet18_Weights.IMAGENET1K_V1`. You can also use `weights=ResNet18_Weights.DEFAULT` to get the most up-to-date weights.
       warnings.warn(msg)
     Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
-
      0%|          | 0.00/44.7M [00:00<?, ?B/s]
     18%|#7        | 7.99M/44.7M [00:00<00:00, 66.9MB/s]
     36%|###5      | 16.0M/44.7M [00:00<00:00, 70.6MB/s]
     58%|#####8    | 26.0M/44.7M [00:00<00:00, 84.9MB/s]
     77%|#######6  | 34.3M/44.7M [00:00<00:00, 68.4MB/s]
    100%|##########| 44.7M/44.7M [00:00<00:00, 78.3MB/s]
+
      0%|          | 0.00/44.7M [00:00<?, ?B/s]
     21%|##        | 9.25M/44.7M [00:00<00:00, 97.0MB/s]
     49%|####8     | 21.9M/44.7M [00:00<00:00, 117MB/s] 
     74%|#######3  | 33.0M/44.7M [00:00<00:00, 80.2MB/s]
    100%|##########| 44.7M/44.7M [00:00<00:00, 102MB/s] 
 
 
 
diff --git a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
index 044a67bde0..7c4915f9a9 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -416,7 +416,7 @@ Run the corresponding model on tensorflow
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  15.514 seconds)
+   **Total running time of the script:** ( 1 minutes  15.887 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 ebbba6b48d..f14a4ce6e9 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
 =================
-**06:00.290** total execution time for **how_to_compile_models** files:
+**06:00.348** total execution time for **how_to_compile_models** files:
 
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:15.514 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:15.887 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)       | 01:15.301 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)       | 01:13.173 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)         | 00:48.878 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)         | 00:49.849 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)       | 00:33.615 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)       | 00:33.582 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)           | 00:29.532 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)           | 00:29.691 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)         | 00:28.036 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)         | 00:27.791 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)         | 00:26.265 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)         | 00:26.084 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)       | 00:23.066 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)       | 00:23.416 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)           | 00:17.623 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)           | 00:18.391 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)             | 00:02.461 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)             | 00:02.482 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
index 84339188d3..38d504f546 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
@@ -723,7 +723,7 @@ well as provides information about the model's performance
     Evaluate inference time cost...
     Execution time summary:
      mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)  
-     2760.7189    2759.9108    2771.6618    2755.6291      4.8687   
+     2759.0047    2758.5342    2762.9447    2756.1885      2.4528   
                
 
 
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 58d6b078ff..1c1b66bab1 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
@@ -433,7 +433,7 @@ Execute on TVM
     Evaluate inference time cost...
     Execution time summary:
      mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)  
-      16.8982      17.0101      17.3807      16.2455       0.4318   
+      16.5858      16.7217      17.1187      15.9205       0.3984   
                
 
 
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 5229345062..2af798f220 100644
--- a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
@@ -127,7 +127,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
     /venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MaskRCNN_ResNet50_FPN_Weights.COCO_V1`. You can also use `weights=MaskRCNN_ResNet50_FPN_Weights.DEFAULT` to get the most up-to-date weights.
       warnings.warn(msg)
     Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
      0%|          | 0.00/170M [00:00<?, ?B/s]
      5%|4         | 7.99M/170M [00:00<00:04, 37.7MB/s]
      9%|8         | 14.9M/170M [00:00<00:03, 51.2MB/s]
     12%|#2        | 20.4M/170M [00:00<00:03, 50.0MB/s]
     15%|#5        | 25.5M/170M [00:00<00:03, 45.8MB/s]
     19%|#8        | 32.0M/170M [00:00<00:03, 37.9MB/s]
     24%|##3       | 40.1M/170M [00:00<00:02, 48.1MB/s]
     27%|##6       | 45.3M/170M [00:01<00:02, 45.1MB/s]
     29%|##9       | 50.0M/170M [00:01<00:02, 44.3MB/s]
     33%|###2      | 56.0M/170M [00:01<00:02, 47.1MB/s]
     37%|###6      | 62.3M/170M [00:01<00:02, 49.8MB/s]
     41%|####1     | 70.4M/170M [00:01<00:01, 58.9MB/s]
     45%|####5     | 76.6M/170M [00:01<00:01, 60.7MB/s]
     49%|####8     | 82.6M/170M [00:01<00:01, 56.9MB/s]
     52%|#####1    | 88.2M/170M [00:01<00:01, 51.2MB/s]
     57%|#####6    | 96.0M/170M [00:01<00:01, 56.4MB/s]
     61%|######1   | 104M/170M [00:02<00:01, 59.2MB/s] 
     65%|######4   | 110M/170M [00:02<00:01, 58.8MB/s
 ]
     68%|######7   | 115M/170M [00:02<00:01, 55.0MB/s]
     74%|#######3  | 125M/170M [00:02<00:00, 66.6MB/s]
     77%|#######7  | 131M/170M [00:02<00:00, 62.8MB/s]
     81%|########1 | 138M/170M [00:02<00:00, 53.1MB/s]
     85%|########4 | 144M/170M [00:02<00:00, 53.8MB/s]
     88%|########8 | 150M/170M [00:03<00:00, 53.0MB/s]
     92%|#########1| 156M/170M [00:03<00:00, 53.9MB/s]
     95%|#########4| 161M/170M [00:03<00:00, 53.7MB/s]
     99%|#########8| 168M/170M [00:03<00:00, 54.5MB/s]
    100%|##########| 170M/170M [00:03<00:00, 53.2MB/s]
+
      0%|          | 0.00/170M [00:00<?, ?B/s]
      5%|5         | 9.16M/170M [00:00<00:01, 96.0MB/s]
     11%|#         | 18.3M/170M [00:00<00:01, 84.7MB/s]
     18%|#7        | 29.9M/170M [00:00<00:01, 100MB/s] 
     24%|##3       | 40.0M/170M [00:00<00:01, 100MB/s]
     33%|###2      | 56.0M/170M [00:00<00:01, 105MB/s]
     40%|###9      | 67.8M/170M [00:00<00:00, 110MB/s]
     46%|####6     | 78.3M/170M [00:00<00:00, 103MB/s]
     52%|#####1    | 88.3M/170M [00:00<00:00, 90.6MB/s]
     59%|#####9    | 101M/170M [00:01<00:00, 101MB/s]  
     66%|######5   | 112M/170M [00:01<00:00, 95.2MB/s]
     72%|#######1  | 122M/170M [00:01<00:00, 95.3MB/s]
     78%|#######7  | 132M/170M [00:01<00:00, 98.9MB/s]
     85%|########4 | 144M/170M [00:01<00:00, 99.0MB/s]
     91%|#########1| 155M/170M [00:01<00:00, 104MB/s] 
     99%|#########9| 168M/170M [00:01<00:00, 114MB/s]
    100%|##########| 170M/170M [00:01<00:00, 103MB/s]
     /venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
       for i in range(dim)
     /venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -296,7 +296,7 @@ Get boxes with score larger than 0.9
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 3 minutes  28.849 seconds)
+   **Total running time of the script:** ( 3 minutes  25.396 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 7f3eb83f67..b1bfd0199a 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -236,7 +236,7 @@ training. Other models require a full post training calibration.
     /venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MobileNet_V2_Weights.IMAGENET1K_V1`. You can also use `weights=MobileNet_V2_Weights.DEFAULT` to get the most up-to-date weights.
       warnings.warn(msg)
     Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
      0%|          | 0.00/13.6M [00:00<?, ?B/s]
     59%|#####8    | 7.99M/13.6M [00:00<00:00, 79.9MB/s]
    100%|##########| 13.6M/13.6M [00:00<00:00, 66.3MB/s]
+
      0%|          | 0.00/13.6M [00:00<?, ?B/s]
     59%|#####8    | 7.99M/13.6M [00:00<00:00, 49.4MB/s]
    100%|##########| 13.6M/13.6M [00:00<00:00, 54.1MB/s]
 
 
 
@@ -418,7 +418,7 @@ Here we give an example of how to measure performance of TVM compiled models.
 
     Execution time summary:
      mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)  
-      90.6435      90.5418      92.8492      90.2445       0.3633   
+      90.6194      90.4477      99.0254      90.2220       0.8892   
                
 
 
@@ -467,7 +467,7 @@ TODO
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  9.190 seconds)
+   **Total running time of the script:** ( 1 minutes  9.150 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 e49bd5a785..f3b1d361d9 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
@@ -432,7 +432,7 @@ Here we give an example of how to measure performance of TVM compiled models.
 
     Execution time summary:
      mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)  
-      120.9832     120.6341     128.4909     119.6394      1.4166   
+      121.2797     121.2729     122.5077     120.3166      0.4146   
                
 
 
@@ -469,7 +469,7 @@ Here we give an example of how to measure performance of TVM compiled models.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 2 minutes  29.178 seconds)
+   **Total running time of the script:** ( 2 minutes  32.735 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 441bae7c63..a6e7d299aa 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -253,7 +253,7 @@ We create a Relay VM to build and execute the model.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  37.785 seconds)
+   **Total running time of the script:** ( 1 minutes  37.360 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 8dda1fccff..a6c9e1d4ed 100644
--- a/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
@@ -166,7 +166,7 @@ Convert and compile model for CPU.
             data: None
       input_sym_arg_type = in_param.infer_type()[0]
     Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
      0%|          | 0/132723 [00:00<?, ?KB/s]
      5%|5         | 6884/132723 [00:00<00:01, 68831.20KB/s]
     12%|#1        | 15412/132723 [00:00<00:01, 78503.86KB/s]
     18%|#7        | 23263/132723 [00:00<00:01, 74839.88KB/s]
     24%|##3       | 31850/132723 [00:00<00:01, 79061.65KB/s]
     30%|##9       | 39781/132723 [00:00<00:01, 66048.12KB/s]
     36%|###6      | 48356/132723 [00:00<00:01, 71890.91KB/s]
     43%|####2     | 56897/132723 [00:00<00:00, 75912.44KB/s]
     49%|####8     | 64718/132723 [00:00<00:00, 76268.91KB/s]
     55%|#####4    | 72504/132723 [00:01<00:00, 62495.16KB/s]
     61%|######1   | 81028/132723 [00:01<00:00, 68337.98KB/s]
     67%|######7   | 89481/132723 [00:01<00:00, 72688.89KB/s]
     74%|#######3  | 98041/132723 [00:01<00:00, 76268.87KB/s]
     80%|########  | 106595/132723 [00:01<00:00, 78898.36KB/s]
     87%|########6 | 115179/132723 [00:01<00:00, 80899.82KB/s]
     93%|#########3| 123764/132723 [00:01<00:00, 82343.45KB/s]
    100%|########
 #9| 132413/132723 [00:01<00:00, 83559.09KB/s]
    100%|##########| 132723/132723 [00:01<00:00, 75796.48KB/s]
+
      0%|          | 0/132723 [00:00<?, ?KB/s]
      5%|4         | 6555/132723 [00:00<00:01, 65536.78KB/s]
     11%|#         | 14530/132723 [00:00<00:01, 73890.94KB/s]
     17%|#6        | 21920/132723 [00:00<00:01, 55509.89KB/s]
     22%|##2       | 29675/132723 [00:00<00:01, 62755.25KB/s]
     27%|##7       | 36350/132723 [00:00<00:02, 45201.06KB/s]
     33%|###3      | 44368/132723 [00:00<00:01, 53726.66KB/s]
     39%|###9      | 52330/132723 [00:00<00:01, 60412.83KB/s]
     45%|####5     | 60274/132723 [00:01<00:01, 65538.15KB/s]
     51%|#####1    | 68319/132723 [00:01<00:00, 69680.13KB/s]
     58%|#####7    | 76355/132723 [00:01<00:00, 72713.74KB/s]
     64%|######3   | 84350/132723 [00:01<00:00, 74788.72KB/s]
     70%|######9   | 92406/132723 [00:01<00:00, 76470.32KB/s]
     76%|#######5  | 100359/132723 [00:01<00:00, 77369.24KB/s]
     82%|########1 | 108228/132723 [00:01<00:00, 73505.70KB/s]
     87%|########7 | 115708/132723 [00:01<00:00, 62549.62KB/s]
     93%|########
 #2| 123138/132723 [00:01<00:00, 65564.97KB/s]
     99%|#########8| 131021/132723 [00:01<00:00, 69122.17KB/s]
    100%|##########| 132723/132723 [00:02<00:00, 66119.05KB/s]
 
 
 
@@ -242,7 +242,7 @@ Display result
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 3 minutes  13.027 seconds)
+   **Total running time of the script:** ( 3 minutes  12.862 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 af936568cd..e1e2a6fef4 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
 
 Computation times
 =================
-**14:23.758** total execution time for **how_to_deploy_models** files:
+**14:21.220** total execution time for **how_to_deploy_models** files:
 
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:28.849 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:25.396 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)                           | 03:13.027 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)                           | 03:12.862 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)           | 02:29.178 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)           | 02:32.735 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)                               | 01:37.785 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)                               | 01:37.360 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)                         | 01:09.190 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)                         | 01:09.150 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``)                   | 00:55.119 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``)                   | 00:55.016 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)                 | 00:37.633 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)                 | 00:36.521 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``)                       | 00:26.707 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)                       | 00:26.123 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)                       | 00:26.263 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``)                       | 00:26.050 | 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 d346a2db82..2e60da5bc8 100644
--- a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
@@ -472,7 +472,7 @@ First let us define two helper functions to get the mobilenet model and a cat im
 
  .. code-block:: none
 
-    Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipcc753a8d-e565-4644-ab16-e3e685295079 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+    Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipf645fbff-4783-4d01-8427-5dd9717de0cc 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 71991bd715..22b94e3964 100644
--- a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
 
 Computation times
 =================
-**00:48.957** total execution time for **how_to_extend_tvm** files:
+**00:49.273** total execution time for **how_to_extend_tvm** files:
 
 +-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:45.386 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:45.703 | 0.0 MB |
 +-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)           | 00:02.490 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)           | 00:02.494 | 0.0 MB |
 +-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)                     | 00:01.073 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)                     | 00:01.069 | 0.0 MB |
 +-------------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``)       | 00:00.008 | 0.0 MB |
 +-------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
index 5d293830f8..b4369e97bf 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: 7480us [7480us] (46.57%; 46.57%)
-    FoldScaleAxis: 8580us [9us] (53.43%; 53.43%)
-            FoldConstant: 8571us [1759us] (53.37%; 99.90%)
-                    InferType: 6812us [6812us] (42.42%; 79.47%)
+    InferType: 7356us [7356us] (46.88%; 46.88%)
+    FoldScaleAxis: 8337us [7us] (53.12%; 53.12%)
+            FoldConstant: 8329us [1675us] (53.08%; 99.91%)
+                    InferType: 6654us [6654us] (42.40%; 79.89%)
 
 
 
@@ -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: 6849us [6849us] (44.91%; 44.91%)
-    FoldScaleAxis: 8401us [6us] (55.09%; 55.09%)
-            FoldConstant: 8394us [1703us] (55.05%; 99.93%)
-                    InferType: 6692us [6692us] (43.88%; 79.71%)
+    InferType: 6724us [6724us] (44.96%; 44.96%)
+    FoldScaleAxis: 8230us [5us] (55.04%; 55.04%)
+            FoldConstant: 8225us [1700us] (55.00%; 99.94%)
+                    InferType: 6525us [6525us] (43.64%; 79.34%)
 
 
 
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 ae752b7eba..ced926aee7 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
@@ -340,7 +340,7 @@ latency of convolution.
 
  .. code-block:: none
 
-    Convolution: 37.816287 ms
+    Convolution: 47.380992 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 7d505f0750..12c3f95b32 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
@@ -657,7 +657,7 @@ be able to run on our build server
 
  .. code-block:: none
 
-    conv2d with tensor core: 13.363971 ms
+    conv2d with tensor core: 13.353380 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 77bf5516ea..bc8b3e43dd 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: 0.019378
-    Baseline: 3.336809
+    Numpy running time: 0.019708
+    Baseline: 3.144211
 
 
 
@@ -238,7 +238,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
 
  .. code-block:: none
 
-    Opt1: 0.325638
+    Opt1: 0.323363
 
 
 
@@ -340,7 +340,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
 
  .. code-block:: none
 
-    Opt2: 0.353265
+    Opt2: 0.351613
 
 
 
@@ -435,7 +435,7 @@ the access pattern for A matrix is more cache friendly.
 
  .. code-block:: none
 
-    Opt3: 0.121025
+    Opt3: 0.119467
 
 
 
@@ -559,7 +559,7 @@ flattening.
 
  .. code-block:: none
 
-    Opt4: 0.109749
+    Opt4: 0.109682
 
 
 
@@ -680,7 +680,7 @@ write to C when all the block results are ready.
 
  .. code-block:: none
 
-    Opt5: 0.111289
+    Opt5: 0.111231
 
 
 
@@ -804,7 +804,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
 
  .. code-block:: none
 
-    Opt6: 0.147143
+    Opt6: 0.147187
 
 
 
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 02e5b8a9b0..0bba560430 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
 
 Computation times
 =================
-**00:35.433** total execution time for **how_to_optimize_operators** files:
+**00:35.075** total execution time for **how_to_optimize_operators** files:
 
 +-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)                       | 00:32.758 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)                       | 00:32.336 | 0.0 MB |
 +-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.573 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.590 | 0.0 MB |
 +-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)             | 00:01.101 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)             | 00:01.148 | 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 87e4638ec7..689d071fa8 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
 
 Computation times
 =================
-**09:16.064** total execution time for **how_to_tune_with_autoscheduler** files:
+**09:10.984** total execution time for **how_to_tune_with_autoscheduler** files:
 
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:34.391 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:41.980 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)             | 01:34.721 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)             | 01:33.775 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)           | 01:03.847 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)           | 01:02.943 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)               | 00:39.083 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)               | 00:28.478 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)             | 00:12.549 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)             | 00:12.355 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)           | 00:11.474 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)           | 00:11.453 | 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 b4b9ec8881..2cd7d556cd 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
@@ -239,483 +239,805 @@ cooperative fetching, unrolling and operator fusion.
                  bias: Buffer(bias_2: Pointer(float32), float32, [1, 512, 1, 1], []),
                  compute: Buffer(compute_2: Pointer(float32), float32, [1, 512, 7, 7], [])}
       buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute} {
-      attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 28;
-      allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
-      allocate(pad_temp.shared: Pointer(shared float32), float32, [72]), storage_scope = shared;
-      allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
-      attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
-        conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
-        conv2d_nchw_1[1] = 0f32
-        conv2d_nchw_1[2] = 0f32
-        conv2d_nchw_1[3] = 0f32
+      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, [392]), storage_scope = shared;
+      allocate(kernel.shared: Pointer(shared float32), float32, [256]), storage_scope = shared;
+      attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+        conv2d_nchw_1: Buffer(conv2d_nchw, float32, [16], [], scope="local", align=16)[0] = 0f32
         conv2d_nchw_1[4] = 0f32
-        conv2d_nchw_1[5] = 0f32
-        conv2d_nchw_1[6] = 0f32
-        conv2d_nchw_1[7] = 0f32
         conv2d_nchw_1[8] = 0f32
+        conv2d_nchw_1[12] = 0f32
+        conv2d_nchw_1[16] = 0f32
+        conv2d_nchw_1[20] = 0f32
+        conv2d_nchw_1[24] = 0f32
+        conv2d_nchw_1[1] = 0f32
+        conv2d_nchw_1[5] = 0f32
         conv2d_nchw_1[9] = 0f32
+        conv2d_nchw_1[13] = 0f32
+        conv2d_nchw_1[17] = 0f32
+        conv2d_nchw_1[21] = 0f32
+        conv2d_nchw_1[25] = 0f32
+        conv2d_nchw_1[2] = 0f32
+        conv2d_nchw_1[6] = 0f32
         conv2d_nchw_1[10] = 0f32
+        conv2d_nchw_1[14] = 0f32
+        conv2d_nchw_1[18] = 0f32
+        conv2d_nchw_1[22] = 0f32
+        conv2d_nchw_1[26] = 0f32
+        conv2d_nchw_1[3] = 0f32
+        conv2d_nchw_1[7] = 0f32
         conv2d_nchw_1[11] = 0f32
-        conv2d_nchw_1[12] = 0f32
-        conv2d_nchw_1[13] = 0f32
+        conv2d_nchw_1[15] = 0f32
+        conv2d_nchw_1[19] = 0f32
+        conv2d_nchw_1[23] = 0f32
+        conv2d_nchw_1[27] = 0f32
         for (rc.outer.outer: int32, 0, 64) {
           for (ry.outer.outer: int32, 0, 3) {
-            let cse_var_2: int32 = (rc.outer.outer*72)
-            let cse_var_1: int32 = (ry.outer.outer*3)
+            let cse_var_2: int32 = (rc.outer.outer*392)
+            let cse_var_1: int32 = (ry.outer.outer*7)
              {
-              attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
-                if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
-                  pad_temp.shared_1: Buffer(pad_temp.shared, float32, [72], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data_3: Buffer(data_2, float32, [25088], [])[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*4), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + fl [...]
-                }
-                if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
-                  pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data_3[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 1), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0f32, dtype=float32)
-                }
-                if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
-                  pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data_3[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 2), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0f32, dtype=float32)
-                }
-                if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
-                  pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data_3[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 3), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0f32, dtype=float32)
-                }
+              attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+              pad_temp.shared_1: Buffer(pad_temp.shared, float32, [392], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data_3: Buffer(data_2, float32, [25088], [])[(((cse_var_2 + cse_var_1) + threadIdx.x_1) - 8)], 0f32, dtype=float32)
+              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+              pad_temp.shared_1[(threadIdx.x_1 + 56)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 1), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 1), 7)) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 56), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 1), 7)*7)) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+              pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 2), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 2), 7)) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 112), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 2), 7)*7)) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+              pad_temp.shared_1[(threadIdx.x_1 + 168)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 3), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 3), 7)) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 168), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 7)*7)) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+              pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 4), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 4), 7)) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 7)*7)) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+              pad_temp.shared_1[(threadIdx.x_1 + 280)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 5), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 5), 7)) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 280), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 7)*7)) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+              pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 6), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 6), 7)) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 336), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 7)*7)) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+              attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+              kernel.shared_1: Buffer(kernel.shared, float32, [256], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3))]
+              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+              kernel.shared_1[(threadIdx.x_2 + 56)] = kernel_3[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 32256)]
+              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+              kernel.shared_1[(threadIdx.x_2 + 112)] = kernel_3[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 64512)]
+              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+              kernel.shared_1[(threadIdx.x_2 + 168)] = kernel_3[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 96768)]
+              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 + 224)] = kernel_3[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 129024)]
               }
-              attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 64)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 64), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 128)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 128), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 192)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 256)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 256), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 320)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 320), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 384)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 448)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 448), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 512)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 512), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 576)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 640)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 640), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 704)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 704), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 768)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 147456)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 832)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 832), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 896)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 896), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 960)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 184320)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1024), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1088), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 221184)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1216), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1280), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1408), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1472), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 294912)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1600), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1664), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 331776)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1792), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1856), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 368640)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1984), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2048), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 405504)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2176), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2240), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 442368)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2368), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2432), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 479232)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2560), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2624), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 516096)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2752), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2816), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 552960)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2944), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3008), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*48)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*48)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*48)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*48)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*48)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*48)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*48)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*7)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*32)]))
+              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*32)]))
+              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 2)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*32)]))
+              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 3)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*32)]))
+              conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 4)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*32)]))
+              conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 5)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*32)]))
+              conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 6)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*32)]))
+              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 8)]))
+              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 8)]))
+              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 8)]))
+              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 8)]))
+              conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 8)]))
+              conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 8)]))
+              conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 8)]))
+              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 16)]))
+              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 16)]))
+              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 16)]))
+              conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 16)]))
+              conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 16)]))
+              conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 16)]))
+              conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 16)]))
+              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 24)]))
+              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 24)]))
+              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 24)]))
+              conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 24)]))
+              conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 24)]))
+              conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 24)]))
+              conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 24)]))
+              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 1)]))
+              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 50)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 1)]))
+              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 51)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 1)]))
+              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 52)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 1)]))
+              conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 53)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 1)]))
+              conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 1)]))
+              conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 1)]))
+              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 9)]))
+              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 50)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 9)]))
+              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 51)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 9)]))
+              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 52)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 9)]))
+              conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 53)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 9)]))
+              conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 9)]))
+              conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 9)]))
+              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 17)]))
+              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 50)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 17)]))
+              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 51)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 17)]))
+              conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 52)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 17)]))
+              conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 53)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 17)]))
+              conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 17)]))
+              conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 17)]))
+              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 25)]))
+              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 50)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 25)]))
+              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 51)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 25)]))
+              conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 52)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 25)]))
+              conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 53)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 25)]))
+              conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 25)]))
+              conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 25)]))
+              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 2)]))
+              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 2)]))
+              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 2)]))
+              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 2)]))
+              conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 2)]))
+              conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 2)]))
+              conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 2)]))
+              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 10)]))
+              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 10)]))
+              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 10)]))
+              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 10)]))
+              conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 10)]))
+              conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 10)]))
+              conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 10)]))
+              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 18)]))
+              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 18)]))
+              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 18)]))
+              conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 18)]))
+              conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 18)]))
+              conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 18)]))
+              conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 18)]))
+              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 26)]))
+              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 26)]))
+              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 26)]))
+              conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 26)]))
+              conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 26)]))
+              conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 26)]))
+              conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 26)]))
+              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 3)]))
+              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 3)]))
+              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 3)]))
+              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 150)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 3)]))
+              conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 151)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 3)]))
+              conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 152)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 3)]))
+              conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 3)]))
+              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 11)]))
+              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 11)]))
+              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 11)]))
+              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 150)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 11)]))
+              conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 151)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 11)]))
+              conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 152)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 11)]))
+              conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 11)]))
+              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 19)]))
+              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 19)]))
+              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 19)]))
+              conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 150)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 19)]))
+              conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 151)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 19)]))
+              conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 152)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 19)]))
+              conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 19)]))
+              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 27)]))
+              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 27)]))
+              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 27)]))
+              conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 150)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 27)]))
+              conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 151)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 27)]))
+              conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 152)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 27)]))
+              conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 27)]))
+              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 4)]))
+              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 4)]))
+              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 4)]))
+              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 4)]))
+              conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 4)]))
+              conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 4)]))
+              conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 4)]))
+              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 12)]))
+              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 12)]))
+              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 12)]))
+              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 12)]))
+              conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 12)]))
+              conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 12)]))
+              conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 12)]))
+              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 20)]))
+              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 20)]))
+              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 20)]))
+              conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 20)]))
+              conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 20)]))
+              conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 20)]))
+              conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 20)]))
+              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 28)]))
+              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 28)]))
+              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 28)]))
+              conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 28)]))
+              conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 28)]))
+              conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 28)]))
+              conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 28)]))
+              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 5)]))
+              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 5)]))
+              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 5)]))
+              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 5)]))
+              conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 5)]))
+              conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 5)]))
+              conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 5)]))
+              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 13)]))
+              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 13)]))
+              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 13)]))
+              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 13)]))
+              conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 13)]))
+              conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 13)]))
+              conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 13)]))
+              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 21)]))
+              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 21)]))
+              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 21)]))
+              conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 21)]))
+              conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 21)]))
+              conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 21)]))
+              conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 21)]))
+              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 29)]))
+              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 29)]))
+              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 29)]))
+              conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 29)]))
+              conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 29)]))
+              conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 29)]))
+              conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 29)]))
+              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 6)]))
+              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 295)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 6)]))
+              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 296)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 6)]))
+              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 6)]))
+              conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 6)]))
+              conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 6)]))
+              conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 300)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 6)]))
+              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 14)]))
+              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 295)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 14)]))
+              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 296)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 14)]))
+              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 14)]))
+              conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 14)]))
+              conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 14)]))
+              conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 300)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 14)]))
+              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 22)]))
+              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 295)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 22)]))
+              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 296)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 22)]))
+              conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 22)]))
+              conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 22)]))
+              conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 22)]))
+              conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 300)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 22)]))
+              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 30)]))
+              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 295)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 30)]))
+              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 296)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 30)]))
+              conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 30)]))
+              conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 30)]))
+              conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 30)]))
+              conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 300)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 30)]))
+              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 7)]))
+              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 7)]))
+              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 7)]))
+              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 7)]))
+              conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 7)]))
+              conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 7)]))
+              conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 7)]))
+              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 15)]))
+              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 15)]))
+              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 15)]))
+              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 15)]))
+              conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 15)]))
+              conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 15)]))
+              conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 15)]))
+              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 23)]))
+              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 23)]))
+              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 23)]))
+              conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 23)]))
+              conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 23)]))
+              conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 23)]))
+              conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 23)]))
+              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 31)]))
+              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 31)]))
+              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 31)]))
+              conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 31)]))
+              conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 31)]))
+              conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 31)]))
+              conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 31)]))
+              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+              pad_temp.shared_1[threadIdx.x_1] = @tir.if_then_else(((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)), data_3[(((cse_var_2 + cse_var_1) + threadIdx.x_1) - 7)], 0f32, dtype=float32)
+              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+              pad_temp.shared_1[(threadIdx.x_1 + 56)] = @tir.if_then_else(((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 1), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 1), 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 56), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 1), 7)*7)) + floormod(threadIdx.x_1, 7)) - 7)], 0f32, dtype=float32)
+              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+              pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 2), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 2), 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 112), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 2), 7)*7)) + floormod(threadIdx.x_1, 7)) - 7)], 0f32, dtype=float32)
+              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+              pad_temp.shared_1[(threadIdx.x_1 + 168)] = @tir.if_then_else(((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 3), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 3), 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 168), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 7)*7)) + floormod(threadIdx.x_1, 7)) - 7)], 0f32, dtype=float32)
+              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+              pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 4), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 4), 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 7)*7)) + floormod(threadIdx.x_1, 7)) - 7)], 0f32, dtype=float32)
+              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+              pad_temp.shared_1[(threadIdx.x_1 + 280)] = @tir.if_then_else(((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 5), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 5), 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 280), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 7)*7)) + floormod(threadIdx.x_1, 7)) - 7)], 0f32, dtype=float32)
+              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+              pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 6), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 6), 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 336), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 7)*7)) + floormod(threadIdx.x_1, 7)) - 7)], 0f32, dtype=float32)
+              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+              kernel.shared_1[threadIdx.x_2] = kernel_3[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 1)]
+              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+              kernel.shared_1[(threadIdx.x_2 + 56)] = kernel_3[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 32257)]
+              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+              kernel.shared_1[(threadIdx.x_2 + 112)] = kernel_3[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 64513)]
+              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+              kernel.shared_1[(threadIdx.x_2 + 168)] = kernel_3[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 96769)]
+              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 + 224)] = kernel_3[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 129025)]
+              }
+              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*7)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*32)]))
+              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*32)]))
+              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 2)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*32)]))
+              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 3)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*32)]))
+              conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 4)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*32)]))
+              conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 5)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*32)]))
+              conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 6)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*32)]))
+              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 8)]))
+              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 8)]))
+              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 8)]))
+              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 8)]))
+              conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 8)]))
+              conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 8)]))
+              conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 8)]))
+              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 16)]))
+              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 16)]))
+              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 16)]))
+              conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 16)]))
+              conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 16)]))
+              conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 16)]))
+              conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 16)]))
+              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 24)]))
+              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 24)]))
+              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 24)]))
+              conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 24)]))
+              conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 24)]))
+              conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 24)]))
+              conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 24)]))
+              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 1)]))
+              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 50)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 1)]))
+              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 51)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 1)]))
+              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 52)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 1)]))
+              conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 53)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 1)]))
+              conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 1)]))
+              conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 1)]))
+              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 9)]))
+              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 50)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 9)]))
+              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 51)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 9)]))
+              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 52)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 9)]))
+              conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 53)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 9)]))
+              conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 9)]))
+              conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 9)]))
+              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 17)]))
+              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 50)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 17)]))
+              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 51)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 17)]))
+              conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 52)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 17)]))
+              conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 53)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 17)]))
+              conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 17)]))
+              conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 17)]))
+              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 25)]))
+              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 50)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 25)]))
+              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 51)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 25)]))
+              conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 52)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 25)]))
+              conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 53)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 25)]))
+              conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 25)]))
+              conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 25)]))
+              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 2)]))
+              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 2)]))
+              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 2)]))
+              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 2)]))
+              conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 2)]))
+              conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 2)]))
+              conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 2)]))
+              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 10)]))
+              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 10)]))
+              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 10)]))
+              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 10)]))
+              conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 10)]))
+              conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 10)]))
+              conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 10)]))
+              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 18)]))
+              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 18)]))
+              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 18)]))
+              conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 18)]))
+              conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 18)]))
+              conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 18)]))
+              conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 18)]))
+              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 26)]))
+              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 26)]))
+              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 26)]))
+              conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 26)]))
+              conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 26)]))
+              conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 26)]))
+              conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 26)]))
+              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 3)]))
+              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 3)]))
+              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 3)]))
+              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 150)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 3)]))
+              conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 151)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 3)]))
+              conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 152)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 3)]))
+              conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 3)]))
+              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 11)]))
+              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 11)]))
+              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 11)]))
+              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 150)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 11)]))
+              conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 151)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 11)]))
+              conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 152)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 11)]))
+              conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 11)]))
+              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 19)]))
+              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 19)]))
+              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 19)]))
+              conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 150)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 19)]))
+              conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 151)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 19)]))
+              conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 152)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 19)]))
+              conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 19)]))
+              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 27)]))
+              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 27)]))
+              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 27)]))
+              conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 150)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 27)]))
+              conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 151)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 27)]))
+              conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 152)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 27)]))
+              conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 27)]))
+              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 4)]))
+              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 4)]))
+              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 4)]))
+              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 4)]))
+              conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 4)]))
+              conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 4)]))
+              conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 4)]))
+              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 12)]))
+              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 12)]))
+              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 12)]))
+              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 12)]))
+              conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 12)]))
+              conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 12)]))
+              conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 12)]))
+              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 20)]))
+              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 20)]))
+              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 20)]))
+              conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 20)]))
+              conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 20)]))
+              conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 20)]))
+              conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 20)]))
+              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 28)]))
+              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 28)]))
+              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 28)]))
+              conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 28)]))
+              conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 28)]))
+              conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 28)]))
+              conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 28)]))
+              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 5)]))
+              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 5)]))
+              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 5)]))
+              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 5)]))
+              conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 5)]))
+              conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 5)]))
+              conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 5)]))
+              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 13)]))
+              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 13)]))
+              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 13)]))
+              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 13)]))
+              conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 13)]))
+              conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 13)]))
+              conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 13)]))
+              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 21)]))
+              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 21)]))
+              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 21)]))
+              conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 21)]))
+              conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 21)]))
+              conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 21)]))
+              conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 21)]))
+              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 29)]))
+              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 29)]))
+              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 29)]))
+              conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 29)]))
+              conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 29)]))
+              conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 29)]))
+              conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 29)]))
+              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 6)]))
+              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 295)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 6)]))
+              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 296)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 6)]))
+              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 6)]))
+              conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 6)]))
+              conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 6)]))
+              conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 300)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 6)]))
+              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 14)]))
+              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 295)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 14)]))
+              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 296)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 14)]))
+              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 14)]))
+              conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 14)]))
+              conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 14)]))
+              conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 300)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 14)]))
+              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 22)]))
+              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 295)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 22)]))
+              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 296)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 22)]))
+              conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 22)]))
+              conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 22)]))
+              conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 22)]))
+              conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 300)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 22)]))
+              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 30)]))
+              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 295)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 30)]))
+              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 296)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 30)]))
+              conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 30)]))
+              conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 30)]))
+              conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 30)]))
+              conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 300)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 30)]))
+              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 7)]))
+              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 7)]))
+              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 7)]))
+              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 7)]))
+              conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 7)]))
+              conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 7)]))
+              conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 7)]))
+              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 15)]))
+              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 15)]))
+              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 15)]))
+              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 15)]))
+              conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 15)]))
+              conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 15)]))
+              conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 15)]))
+              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 23)]))
+              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 23)]))
+              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 23)]))
+              conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 23)]))
+              conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 23)]))
+              conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 23)]))
+              conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 23)]))
+              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 31)]))
+              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 31)]))
+              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 31)]))
+              conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 31)]))
+              conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 31)]))
+              conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 31)]))
+              conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 31)]))
+              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+              pad_temp.shared_1[threadIdx.x_1] = @tir.if_then_else((((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data_3[(((cse_var_2 + cse_var_1) + threadIdx.x_1) - 6)], 0f32, dtype=float32)
+              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+              pad_temp.shared_1[(threadIdx.x_1 + 56)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 1), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 1), 7)) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 56), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 1), 7)*7)) + floormod(threadIdx.x_1, 7)) - 6)], 0f32, dtype=float32)
+              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+              pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 2), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 2), 7)) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 112), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 2), 7)*7)) + floormod(threadIdx.x_1, 7)) - 6)], 0f32, dtype=float32)
+              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+              pad_temp.shared_1[(threadIdx.x_1 + 168)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 3), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 3), 7)) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 168), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 7)*7)) + floormod(threadIdx.x_1, 7)) - 6)], 0f32, dtype=float32)
+              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+              pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 4), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 4), 7)) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 7)*7)) + floormod(threadIdx.x_1, 7)) - 6)], 0f32, dtype=float32)
+              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+              pad_temp.shared_1[(threadIdx.x_1 + 280)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 5), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 5), 7)) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 280), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 7)*7)) + floormod(threadIdx.x_1, 7)) - 6)], 0f32, dtype=float32)
+              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+              pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 6), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 6), 7)) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 336), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 7)*7)) + floormod(threadIdx.x_1, 7)) - 6)], 0f32, dtype=float32)
+              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+              kernel.shared_1[threadIdx.x_2] = kernel_3[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 2)]
+              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+              kernel.shared_1[(threadIdx.x_2 + 56)] = kernel_3[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 32258)]
+              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+              kernel.shared_1[(threadIdx.x_2 + 112)] = kernel_3[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 64514)]
+              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+              kernel.shared_1[(threadIdx.x_2 + 168)] = kernel_3[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 96770)]
+              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 + 224)] = kernel_3[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 129026)]
+              }
+              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*7)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*32)]))
+              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*32)]))
+              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 2)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*32)]))
+              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 3)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*32)]))
+              conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 4)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*32)]))
+              conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 5)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*32)]))
+              conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 6)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*32)]))
+              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 8)]))
+              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 8)]))
+              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 8)]))
+              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 8)]))
+              conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 8)]))
+              conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 8)]))
+              conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 8)]))
+              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 16)]))
+              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 16)]))
+              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 16)]))
+              conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 16)]))
+              conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 16)]))
+              conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 16)]))
+              conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 16)]))
+              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 24)]))
+              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 24)]))
+              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 24)]))
+              conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 24)]))
+              conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 24)]))
+              conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 24)]))
+              conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 24)]))
+              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 1)]))
+              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 50)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 1)]))
+              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 51)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 1)]))
+              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 52)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 1)]))
+              conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 53)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 1)]))
+              conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 1)]))
+              conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 1)]))
+              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 9)]))
+              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 50)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 9)]))
+              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 51)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 9)]))
+              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 52)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 9)]))
+              conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 53)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 9)]))
+              conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 9)]))
+              conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 9)]))
+              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 17)]))
+              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 50)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 17)]))
+              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 51)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 17)]))
+              conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 52)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 17)]))
+              conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 53)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 17)]))
+              conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 17)]))
+              conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 17)]))
+              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 25)]))
+              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 50)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 25)]))
+              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 51)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 25)]))
+              conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 52)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 25)]))
+              conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 53)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 25)]))
+              conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 25)]))
+              conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 25)]))
+              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 2)]))
+              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 2)]))
+              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 2)]))
+              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 2)]))
+              conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 2)]))
+              conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 2)]))
+              conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 2)]))
+              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 10)]))
+              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 10)]))
+              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 10)]))
+              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 10)]))
+              conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 10)]))
+              conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 10)]))
+              conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 10)]))
+              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 18)]))
+              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 18)]))
+              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 18)]))
+              conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 18)]))
+              conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 18)]))
+              conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 18)]))
+              conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 18)]))
+              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 26)]))
+              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 26)]))
+              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 26)]))
+              conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 26)]))
+              conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 26)]))
+              conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 26)]))
+              conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 26)]))
+              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 3)]))
+              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 3)]))
+              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 3)]))
+              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 150)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 3)]))
+              conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 151)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 3)]))
+              conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 152)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 3)]))
+              conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 3)]))
+              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 11)]))
+              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 11)]))
+              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 11)]))
+              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 150)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 11)]))
+              conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 151)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 11)]))
+              conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 152)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 11)]))
+              conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 11)]))
+              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 19)]))
+              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 19)]))
+              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 19)]))
+              conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 150)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 19)]))
+              conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 151)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 19)]))
+              conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 152)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 19)]))
+              conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 19)]))
+              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 27)]))
+              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 27)]))
+              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 27)]))
+              conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 150)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 27)]))
+              conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 151)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 27)]))
+              conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 152)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 27)]))
+              conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 27)]))
+              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 4)]))
+              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 4)]))
+              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 4)]))
+              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 4)]))
+              conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 4)]))
+              conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 4)]))
+              conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 4)]))
+              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 12)]))
+              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 12)]))
+              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 12)]))
+              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 12)]))
+              conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 12)]))
+              conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 12)]))
+              conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 12)]))
+              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 20)]))
+              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 20)]))
+              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 20)]))
+              conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 20)]))
+              conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 20)]))
+              conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 20)]))
+              conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 20)]))
+              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 28)]))
+              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 28)]))
+              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 28)]))
+              conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 28)]))
+              conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 28)]))
+              conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 28)]))
+              conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 28)]))
+              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 5)]))
+              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 5)]))
+              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 5)]))
+              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 5)]))
+              conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 5)]))
+              conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 5)]))
+              conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 5)]))
+              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 13)]))
+              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 13)]))
+              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 13)]))
+              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 13)]))
+              conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 13)]))
+              conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 13)]))
+              conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 13)]))
+              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 21)]))
+              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 21)]))
+              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 21)]))
+              conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 21)]))
+              conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 21)]))
+              conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 21)]))
+              conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 21)]))
+              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 29)]))
+              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 29)]))
+              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 29)]))
+              conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 29)]))
+              conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 29)]))
+              conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 29)]))
+              conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 29)]))
+              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 6)]))
+              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 295)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 6)]))
+              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 296)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 6)]))
+              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 6)]))
+              conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 6)]))
+              conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 6)]))
+              conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 300)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 6)]))
+              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 14)]))
+              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 295)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 14)]))
+              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 296)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 14)]))
+              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 14)]))
+              conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 14)]))
+              conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 14)]))
+              conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 300)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 14)]))
+              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 22)]))
+              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 295)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 22)]))
+              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 296)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 22)]))
+              conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 22)]))
+              conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 22)]))
+              conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 22)]))
+              conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 300)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 22)]))
+              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 30)]))
+              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 295)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 30)]))
+              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 296)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 30)]))
+              conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 30)]))
+              conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 30)]))
+              conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 30)]))
+              conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 300)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 30)]))
+              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 7)]))
+              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 7)]))
+              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 7)]))
+              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 7)]))
+              conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 7)]))
+              conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 7)]))
+              conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 7)]))
+              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 15)]))
+              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 15)]))
+              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 15)]))
+              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 15)]))
+              conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 15)]))
+              conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 15)]))
+              conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 15)]))
+              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 23)]))
+              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 23)]))
+              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 23)]))
+              conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 23)]))
+              conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 23)]))
+              conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 23)]))
+              conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 23)]))
+              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 31)]))
+              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 31)]))
+              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 31)]))
+              conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 31)]))
+              conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 31)]))
+              conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 31)]))
+              conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 31)]))
             }
           }
         }
-        for (i1.inner: int32, 0, 2) {
-          for (i3.inner: int32, 0, 7) {
-            compute_3: Buffer(compute_2, float32, [25088], [])[(((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias_3: Buffer(bias_2, float32, [512], [])[(((floordiv(blockIdx.x, 7)*128) + (threadIdx.x*2)) + i1.inner)]), 0f32)
-          }
+        for (i1.inner: int32, 0, 4) {
+          compute_3: Buffer(compute_2, float32, [25088], [])[((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7))] = max((conv2d_nchw_1[i1.inner] + bias_3: Buffer(bias_2, float32, [512], [])[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
+          compute_3[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 1)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias_3[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
+          compute_3[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 2)] = max((conv2d_nchw_1[(i1.inner + 8)] + bias_3[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
+          compute_3[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 3)] = max((conv2d_nchw_1[(i1.inner + 12)] + bias_3[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
+          compute_3[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 4)] = max((conv2d_nchw_1[(i1.inner + 16)] + bias_3[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
+          compute_3[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 5)] = max((conv2d_nchw_1[(i1.inner + 20)] + bias_3[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
+          compute_3[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 6)] = max((conv2d_nchw_1[(i1.inner + 24)] + bias_3[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
         }
       }
     }
@@ -770,7 +1092,7 @@ We build the binary and check its correctness and performance.
 
  .. code-block:: none
 
-    Execution time of this operator: 0.356 ms
+    Execution time of this operator: 0.365 ms
 
 
 
@@ -818,37 +1140,37 @@ 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=1)
-    conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
-    conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
+    conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=4)
+    conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
+    conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=8)
     conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
     conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
     conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
-    conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
+    conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
     conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
     conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
-    conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
+    conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
     conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
-    conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-    conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
-    conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
+    conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=7)
+    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=8)
     conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
     conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
     conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
-    conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+    conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
     s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
     compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
     compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
     compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
-    compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
-    compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
+    compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=4)
+    compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
     compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
     compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
-    compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+    compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
     compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
-    compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
+    compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
     compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
-    compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
+    compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=7)
     s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
     s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
     kernel_shared = s.cache_read(kernel, "shared", [conv2d_nchw])
@@ -867,14 +1189,14 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
     kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
     kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
     s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-    kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
+    kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
     s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
     pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
-    pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=4)
+    pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
     s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-    pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
+    pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=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", 512)
+    s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
     s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
 
     CUDA source code:
@@ -892,430 +1214,770 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
       #define int64_t long long
       #define uint64_t unsigned long long
     #endif
-    extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
-      float conv2d_nchw[14];
-      __shared__ float pad_temp_shared[72];
-      __shared__ float kernel_shared[3072];
+    extern "C" __global__ void __launch_bounds__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+      float conv2d_nchw[28];
+      __shared__ float pad_temp_shared[392];
+      __shared__ float kernel_shared[256];
       conv2d_nchw[0] = 0.000000e+00f;
-      conv2d_nchw[1] = 0.000000e+00f;
-      conv2d_nchw[2] = 0.000000e+00f;
-      conv2d_nchw[3] = 0.000000e+00f;
       conv2d_nchw[4] = 0.000000e+00f;
-      conv2d_nchw[5] = 0.000000e+00f;
-      conv2d_nchw[6] = 0.000000e+00f;
-      conv2d_nchw[7] = 0.000000e+00f;
       conv2d_nchw[8] = 0.000000e+00f;
+      conv2d_nchw[12] = 0.000000e+00f;
+      conv2d_nchw[16] = 0.000000e+00f;
+      conv2d_nchw[20] = 0.000000e+00f;
+      conv2d_nchw[24] = 0.000000e+00f;
+      conv2d_nchw[1] = 0.000000e+00f;
+      conv2d_nchw[5] = 0.000000e+00f;
       conv2d_nchw[9] = 0.000000e+00f;
+      conv2d_nchw[13] = 0.000000e+00f;
+      conv2d_nchw[17] = 0.000000e+00f;
+      conv2d_nchw[21] = 0.000000e+00f;
+      conv2d_nchw[25] = 0.000000e+00f;
+      conv2d_nchw[2] = 0.000000e+00f;
+      conv2d_nchw[6] = 0.000000e+00f;
       conv2d_nchw[10] = 0.000000e+00f;
+      conv2d_nchw[14] = 0.000000e+00f;
+      conv2d_nchw[18] = 0.000000e+00f;
+      conv2d_nchw[22] = 0.000000e+00f;
+      conv2d_nchw[26] = 0.000000e+00f;
+      conv2d_nchw[3] = 0.000000e+00f;
+      conv2d_nchw[7] = 0.000000e+00f;
       conv2d_nchw[11] = 0.000000e+00f;
-      conv2d_nchw[12] = 0.000000e+00f;
-      conv2d_nchw[13] = 0.000000e+00f;
+      conv2d_nchw[15] = 0.000000e+00f;
+      conv2d_nchw[19] = 0.000000e+00f;
+      conv2d_nchw[23] = 0.000000e+00f;
+      conv2d_nchw[27] = 0.000000e+00f;
       for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
         for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
           __syncthreads();
-          if (((int)threadIdx.x) < 18) {
-            pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
-          }
-          if (((int)threadIdx.x) < 18) {
-            pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
+          pad_temp_shared[((int)threadIdx.x)] = ((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[((((rc_outer_outer * 392) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) - 8)] : 0.000000e+00f);
+          pad_temp_shared[(((int)threadIdx.x) + 56)] = ((((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 1) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 1) % 7)) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 56) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 1) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+          pad_temp_shared[(((int)threadIdx.x) + 112)] = ((((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 2) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 2) % 7)) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 112) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 2) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+          pad_temp_shared[(((int)threadIdx.x) + 168)] = ((((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 3) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 3) % 7)) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 168) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 3) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+          pad_temp_shared[(((int)threadIdx.x) + 224)] = ((((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 4) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 4) % 7)) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 4) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+          pad_temp_shared[(((int)threadIdx.x) + 280)] = ((((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 5) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 5) % 7)) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 280) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 5) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+          pad_temp_shared[(((int)threadIdx.x) + 336)] = ((((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 6) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 6) % 7)) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 336) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 6) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+          kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 7) * 9)) + (ry_outer_outer * 3))];
+          kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 7) * 9)) + (ry_outer_outer * 3)) + 32256)];
+          kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 7) * 9)) + (ry_outer_outer * 3)) + 64512)];
+          kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 7) * 9)) + (ry_outer_outer * 3)) + 96768)];
+          if (((int)threadIdx.x) < 32) {
+            kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 7) * 9)) + (ry_outer_outer * 3)) + 129024)];
           }
-          if (((int)threadIdx.x) < 18) {
-            pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
+          __syncthreads();
+          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 7)] * kernel_shared[((((int)threadIdx.x) / 7) * 32)]));
+          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1)] * kernel_shared[((((int)threadIdx.x) / 7) * 32)]));
+          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 2)] * kernel_shared[((((int)threadIdx.x) / 7) * 32)]));
+          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 3)] * kernel_shared[((((int)threadIdx.x) / 7) * 32)]));
+          conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 4)] * kernel_shared[((((int)threadIdx.x) / 7) * 32)]));
+          conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 5)] * kernel_shared[((((int)threadIdx.x) / 7) * 32)]));
+          conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 6)] * kernel_shared[((((int)threadIdx.x) / 7) * 32)]));
+          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 8)]));
+          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 8)]));
+          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 8)]));
+          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 8)]));
+          conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 8)]));
+          conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 8)]));
+          conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 8)]));
+          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 16)]));
+          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 16)]));
+          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 16)]));
+          conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 16)]));
+          conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 16)]));
+          conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 16)]));
+          conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 16)]));
+          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 24)]));
+          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 24)]));
+          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 24)]));
+          conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 24)]));
+          conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 24)]));
+          conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 24)]));
+          conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 24)]));
+          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 49)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 1)]));
+          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 50)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 1)]));
+          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 51)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 1)]));
+          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 52)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 1)]));
+          conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 53)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 1)]));
+          conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 1)]));
+          conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 1)]));
+          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 49)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 9)]));
+          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 50)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 9)]));
+          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 51)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 9)]));
+          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 52)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 9)]));
+          conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 53)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 9)]));
+          conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 9)]));
+          conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 9)]));
+          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 49)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 17)]));
+          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 50)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 17)]));
+          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 51)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 17)]));
+          conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 52)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 17)]));
+          conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 53)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 17)]));
+          conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 17)]));
+          conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 17)]));
+          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 49)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 25)]));
+          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 50)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 25)]));
+          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 51)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 25)]));
+          conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 52)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 25)]));
+          conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 53)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 25)]));
+          conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 25)]));
+          conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 25)]));
+          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 2)]));
+          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 2)]));
+          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 2)]));
+          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 2)]));
+          conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 2)]));
+          conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 2)]));
+          conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 2)]));
+          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 10)]));
+          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 10)]));
+          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 10)]));
+          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 10)]));
+          conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 10)]));
+          conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 10)]));
+          conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 10)]));
+          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 18)]));
+          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 18)]));
+          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 18)]));
+          conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 18)]));
+          conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 18)]));
+          conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 18)]));
+          conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 18)]));
+          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 26)]));
+          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 26)]));
+          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 26)]));
+          conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 26)]));
+          conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 26)]));
+          conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 26)]));
+          conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 26)]));
+          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 3)]));
+          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 3)]));
+          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 3)]));
+          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 150)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 3)]));
+          conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 151)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 3)]));
+          conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 152)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 3)]));
+          conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 3)]));
+          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 11)]));
+          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 11)]));
+          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 11)]));
+          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 150)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 11)]));
+          conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 151)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 11)]));
+          conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 152)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 11)]));
+          conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 11)]));
+          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 19)]));
+          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 19)]));
+          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 19)]));
+          conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 150)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 19)]));
+          conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 151)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 19)]));
+          conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 152)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 19)]));
+          conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 19)]));
+          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 27)]));
+          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 27)]));
+          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 27)]));
+          conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 150)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 27)]));
+          conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 151)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 27)]));
+          conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 152)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 27)]));
+          conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 27)]));
+          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 4)]));
+          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 4)]));
+          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 4)]));
+          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 4)]));
+          conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 4)]));
+          conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 4)]));
+          conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 4)]));
+          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 12)]));
+          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 12)]));
+          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 12)]));
+          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 12)]));
+          conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 12)]));
+          conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 12)]));
+          conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 12)]));
+          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 20)]));
+          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 20)]));
+          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 20)]));
+          conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 20)]));
+          conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 20)]));
+          conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 20)]));
+          conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 20)]));
+          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 28)]));
+          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 28)]));
+          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 28)]));
+          conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 28)]));
+          conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 28)]));
+          conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 28)]));
+          conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 28)]));
+          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 5)]));
+          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 5)]));
+          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 5)]));
+          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 5)]));
+          conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 5)]));
+          conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 5)]));
+          conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 5)]));
+          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 13)]));
+          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 13)]));
+          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 13)]));
+          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 13)]));
+          conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 13)]));
+          conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 13)]));
+          conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 13)]));
+          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 21)]));
+          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 21)]));
+          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 21)]));
+          conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 21)]));
+          conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 21)]));
+          conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 21)]));
+          conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 21)]));
+          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 29)]));
+          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 29)]));
+          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 29)]));
+          conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 29)]));
+          conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 29)]));
+          conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 29)]));
+          conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 29)]));
+          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 294)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 6)]));
+          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 295)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 6)]));
+          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 296)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 6)]));
+          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 6)]));
+          conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 6)]));
+          conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 6)]));
+          conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 300)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 6)]));
+          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 294)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 14)]));
+          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 295)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 14)]));
+          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 296)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 14)]));
+          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 14)]));
+          conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 14)]));
+          conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 14)]));
+          conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 300)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 14)]));
+          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 294)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 22)]));
+          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 295)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 22)]));
+          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 296)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 22)]));
+          conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 22)]));
+          conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 22)]));
+          conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 22)]));
+          conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 300)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 22)]));
+          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 294)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 30)]));
+          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 295)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 30)]));
+          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 296)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 30)]));
+          conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 30)]));
+          conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 30)]));
+          conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 30)]));
+          conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 300)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 30)]));
+          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 7)]));
+          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 7)]));
+          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 7)]));
+          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 7)]));
+          conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 7)]));
+          conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 7)]));
+          conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 7)]));
+          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 15)]));
+          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 15)]));
+          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 15)]));
+          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 15)]));
+          conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 15)]));
+          conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 15)]));
+          conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 15)]));
+          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 23)]));
+          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 23)]));
+          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 23)]));
+          conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 23)]));
+          conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 23)]));
+          conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 23)]));
+          conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 23)]));
+          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 31)]));
+          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 31)]));
+          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 31)]));
+          conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 31)]));
+          conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 31)]));
+          conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 31)]));
+          conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 31)]));
+          __syncthreads();
+          pad_temp_shared[((int)threadIdx.x)] = (((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) ? data[((((rc_outer_outer * 392) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) - 7)] : 0.000000e+00f);
+          pad_temp_shared[(((int)threadIdx.x) + 56)] = (((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 1) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 56) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 1) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 7)] : 0.000000e+00f);
+          pad_temp_shared[(((int)threadIdx.x) + 112)] = (((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 2) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 112) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 2) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 7)] : 0.000000e+00f);
+          pad_temp_shared[(((int)threadIdx.x) + 168)] = (((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 3) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 3) % 7)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 168) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 3) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 7)] : 0.000000e+00f);
+          pad_temp_shared[(((int)threadIdx.x) + 224)] = (((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 4) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 4) % 7)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 4) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 7)] : 0.000000e+00f);
+          pad_temp_shared[(((int)threadIdx.x) + 280)] = (((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 5) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 5) % 7)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 280) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 5) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 7)] : 0.000000e+00f);
+          pad_temp_shared[(((int)threadIdx.x) + 336)] = (((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 6) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 6) % 7)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 336) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 6) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 7)] : 0.000000e+00f);
+          kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 7) * 9)) + (ry_outer_outer * 3)) + 1)];
+          kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 7) * 9)) + (ry_outer_outer * 3)) + 32257)];
+          kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 7) * 9)) + (ry_outer_outer * 3)) + 64513)];
+          kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 7) * 9)) + (ry_outer_outer * 3)) + 96769)];
+          if (((int)threadIdx.x) < 32) {
+            kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 7) * 9)) + (ry_outer_outer * 3)) + 129025)];
           }
-          if (((int)threadIdx.x) < 18) {
-            pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
+          __syncthreads();
+          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 7)] * kernel_shared[((((int)threadIdx.x) / 7) * 32)]));
+          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1)] * kernel_shared[((((int)threadIdx.x) / 7) * 32)]));
+          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 2)] * kernel_shared[((((int)threadIdx.x) / 7) * 32)]));
+          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 3)] * kernel_shared[((((int)threadIdx.x) / 7) * 32)]));
+          conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 4)] * kernel_shared[((((int)threadIdx.x) / 7) * 32)]));
+          conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 5)] * kernel_shared[((((int)threadIdx.x) / 7) * 32)]));
+          conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 6)] * kernel_shared[((((int)threadIdx.x) / 7) * 32)]));
+          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 8)]));
+          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 8)]));
+          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 8)]));
+          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 8)]));
+          conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 8)]));
+          conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 8)]));
+          conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 8)]));
+          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 16)]));
+          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 16)]));
+          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 16)]));
+          conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 16)]));
+          conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 16)]));
+          conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 16)]));
+          conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 16)]));
+          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 24)]));
+          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 24)]));
+          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 24)]));
+          conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 24)]));
+          conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 24)]));
+          conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 24)]));
+          conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 24)]));
+          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 49)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 1)]));
+          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 50)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 1)]));
+          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 51)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 1)]));
+          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 52)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 1)]));
+          conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 53)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 1)]));
+          conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 1)]));
+          conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 1)]));
+          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 49)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 9)]));
+          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 50)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 9)]));
+          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 51)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 9)]));
+          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 52)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 9)]));
+          conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 53)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 9)]));
+          conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 9)]));
+          conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 9)]));
+          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 49)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 17)]));
+          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 50)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 17)]));
+          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 51)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 17)]));
+          conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 52)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 17)]));
+          conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 53)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 17)]));
+          conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 17)]));
+          conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 17)]));
+          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 49)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 25)]));
+          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 50)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 25)]));
+          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 51)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 25)]));
+          conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 52)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 25)]));
+          conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 53)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 25)]));
+          conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 25)]));
+          conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 25)]));
+          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 2)]));
+          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 2)]));
+          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 2)]));
+          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 2)]));
+          conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 2)]));
+          conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 2)]));
+          conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 2)]));
+          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 10)]));
+          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 10)]));
+          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 10)]));
+          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 10)]));
+          conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 10)]));
+          conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 10)]));
+          conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 10)]));
+          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 18)]));
+          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 18)]));
+          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 18)]));
+          conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 18)]));
+          conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 18)]));
+          conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 18)]));
+          conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 18)]));
+          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 26)]));
+          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 26)]));
+          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 26)]));
+          conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 26)]));
+          conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 26)]));
+          conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 26)]));
+          conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 26)]));
+          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 3)]));
+          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 3)]));
+          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 3)]));
+          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 150)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 3)]));
+          conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 151)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 3)]));
+          conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 152)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 3)]));
+          conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 3)]));
+          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 11)]));
+          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 11)]));
+          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 11)]));
+          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 150)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 11)]));
+          conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 151)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 11)]));
+          conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 152)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 11)]));
+          conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 11)]));
+          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 19)]));
+          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 19)]));
+          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 19)]));
+          conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 150)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 19)]));
+          conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 151)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 19)]));
+          conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 152)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 19)]));
+          conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 19)]));
+          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 27)]));
+          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 27)]));
+          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 27)]));
+          conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 150)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 27)]));
+          conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 151)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 27)]));
+          conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 152)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 27)]));
+          conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 27)]));
+          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 4)]));
+          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 4)]));
+          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 4)]));
+          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 4)]));
+          conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 4)]));
+          conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 4)]));
+          conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 4)]));
+          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 12)]));
+          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 12)]));
+          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 12)]));
+          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 12)]));
+          conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 12)]));
+          conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 12)]));
+          conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 12)]));
+          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 20)]));
+          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 20)]));
+          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 20)]));
+          conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 20)]));
+          conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 20)]));
+          conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 20)]));
+          conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 20)]));
+          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 28)]));
+          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 28)]));
+          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 28)]));
+          conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 28)]));
+          conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 28)]));
+          conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 28)]));
+          conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 28)]));
+          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 5)]));
+          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 5)]));
+          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 5)]));
+          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 5)]));
+          conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 5)]));
+          conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 5)]));
+          conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 5)]));
+          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 13)]));
+          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 13)]));
+          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 13)]));
+          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 13)]));
+          conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 13)]));
+          conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 13)]));
+          conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 13)]));
+          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 21)]));
+          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 21)]));
+          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 21)]));
+          conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 21)]));
+          conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 21)]));
+          conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 21)]));
+          conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 21)]));
+          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 29)]));
+          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 29)]));
+          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 29)]));
+          conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 29)]));
+          conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 29)]));
+          conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 29)]));
+          conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 29)]));
+          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 294)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 6)]));
+          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 295)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 6)]));
+          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 296)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 6)]));
+          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 6)]));
+          conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 6)]));
+          conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 6)]));
+          conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 300)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 6)]));
+          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 294)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 14)]));
+          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 295)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 14)]));
+          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 296)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 14)]));
+          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 14)]));
+          conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 14)]));
+          conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 14)]));
+          conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 300)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 14)]));
+          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 294)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 22)]));
+          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 295)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 22)]));
+          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 296)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 22)]));
+          conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 22)]));
+          conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 22)]));
+          conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 22)]));
+          conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 300)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 22)]));
+          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 294)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 30)]));
+          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 295)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 30)]));
+          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 296)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 30)]));
+          conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 30)]));
+          conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 30)]));
+          conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 30)]));
+          conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 300)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 30)]));
+          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 7)]));
+          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 7)]));
+          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 7)]));
+          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 7)]));
+          conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 7)]));
+          conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 7)]));
+          conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 7)]));
+          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 15)]));
+          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 15)]));
+          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 15)]));
+          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 15)]));
+          conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 15)]));
+          conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 15)]));
+          conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 15)]));
+          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 23)]));
+          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 23)]));
+          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 23)]));
+          conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 23)]));
+          conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 23)]));
+          conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 23)]));
+          conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 23)]));
+          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 31)]));
+          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 31)]));
+          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 31)]));
+          conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 31)]));
+          conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 31)]));
+          conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 31)]));
+          conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 31)]));
+          __syncthreads();
+          pad_temp_shared[((int)threadIdx.x)] = ((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[((((rc_outer_outer * 392) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) - 6)] : 0.000000e+00f);
+          pad_temp_shared[(((int)threadIdx.x) + 56)] = ((((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 1) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 1) % 7)) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 56) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 1) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 6)] : 0.000000e+00f);
+          pad_temp_shared[(((int)threadIdx.x) + 112)] = ((((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 2) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 2) % 7)) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 112) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 2) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 6)] : 0.000000e+00f);
+          pad_temp_shared[(((int)threadIdx.x) + 168)] = ((((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 3) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 3) % 7)) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 168) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 3) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 6)] : 0.000000e+00f);
+          pad_temp_shared[(((int)threadIdx.x) + 224)] = ((((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 4) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 4) % 7)) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 4) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 6)] : 0.000000e+00f);
+          pad_temp_shared[(((int)threadIdx.x) + 280)] = ((((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 5) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 5) % 7)) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 280) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 5) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 6)] : 0.000000e+00f);
+          pad_temp_shared[(((int)threadIdx.x) + 336)] = ((((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 6) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 6) % 7)) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 336) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 6) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 6)] : 0.000000e+00f);
+          kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 7) * 9)) + (ry_outer_outer * 3)) + 2)];
+          kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 7) * 9)) + (ry_outer_outer * 3)) + 32258)];
+          kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 7) * 9)) + (ry_outer_outer * 3)) + 64514)];
+          kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 7) * 9)) + (ry_outer_outer * 3)) + 96770)];
+          if (((int)threadIdx.x) < 32) {
+            kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 7) * 9)) + (ry_outer_outer * 3)) + 129026)];
           }
-          kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
-          kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
-          kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
-          kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
-          kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
-          kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
-          kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
-          kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
-          kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
-          kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
-          kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
-          kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
-          kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
-          kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
-          kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
-          kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
           __syncthreads();
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 48)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 48)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 48)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 48)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 48)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 48)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 48)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 7)] * kernel_shared[((((int)threadIdx.x) / 7) * 32)]));
+          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1)] * kernel_shared[((((int)threadIdx.x) / 7) * 32)]));
+          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 2)] * kernel_shared[((((int)threadIdx.x) / 7) * 32)]));
+          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 3)] * kernel_shared[((((int)threadIdx.x) / 7) * 32)]));
+          conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 4)] * kernel_shared[((((int)threadIdx.x) / 7) * 32)]));
+          conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 5)] * kernel_shared[((((int)threadIdx.x) / 7) * 32)]));
+          conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 6)] * kernel_shared[((((int)threadIdx.x) / 7) * 32)]));
+          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 8)]));
+          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 8)]));
+          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 8)]));
+          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 8)]));
+          conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 8)]));
+          conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 8)]));
+          conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 8)]));
+          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 16)]));
+          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 16)]));
+          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 16)]));
+          conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 16)]));
+          conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 16)]));
+          conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 16)]));
+          conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 16)]));
+          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 24)]));
+          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 24)]));
+          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 24)]));
+          conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 24)]));
+          conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 24)]));
+          conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 24)]));
+          conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 24)]));
+          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 49)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 1)]));
+          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 50)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 1)]));
+          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 51)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 1)]));
+          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 52)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 1)]));
+          conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 53)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 1)]));
+          conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 1)]));
+          conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 1)]));
+          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 49)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 9)]));
+          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 50)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 9)]));
+          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 51)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 9)]));
+          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 52)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 9)]));
+          conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 53)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 9)]));
+          conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 9)]));
+          conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 9)]));
+          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 49)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 17)]));
+          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 50)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 17)]));
+          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 51)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 17)]));
+          conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 52)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 17)]));
+          conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 53)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 17)]));
+          conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 17)]));
+          conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 17)]));
+          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 49)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 25)]));
+          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 50)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 25)]));
+          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 51)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 25)]));
+          conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 52)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 25)]));
+          conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 53)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 25)]));
+          conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 25)]));
+          conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 25)]));
+          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 2)]));
+          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 2)]));
+          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 2)]));
+          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 2)]));
+          conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 2)]));
+          conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 2)]));
+          conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 2)]));
+          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 10)]));
+          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 10)]));
+          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 10)]));
+          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 10)]));
+          conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 10)]));
+          conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 10)]));
+          conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 10)]));
+          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 18)]));
+          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 18)]));
+          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 18)]));
+          conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 18)]));
+          conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 18)]));
+          conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 18)]));
+          conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 18)]));
+          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 26)]));
+          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 26)]));
+          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 26)]));
+          conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 26)]));
+          conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 26)]));
+          conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 26)]));
+          conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 26)]));
+          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 3)]));
+          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 3)]));
+          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 3)]));
+          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 150)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 3)]));
+          conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 151)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 3)]));
+          conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 152)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 3)]));
+          conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 3)]));
+          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 11)]));
+          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 11)]));
+          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 11)]));
+          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 150)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 11)]));
+          conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 151)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 11)]));
+          conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 152)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 11)]));
+          conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 11)]));
+          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 19)]));
+          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 19)]));
+          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 19)]));
+          conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 150)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 19)]));
+          conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 151)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 19)]));
+          conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 152)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 19)]));
+          conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 19)]));
+          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 27)]));
+          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 27)]));
+          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 27)]));
+          conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 150)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 27)]));
+          conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 151)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 27)]));
+          conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 152)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 27)]));
+          conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 27)]));
+          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 4)]));
+          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 4)]));
+          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 4)]));
+          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 4)]));
+          conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 4)]));
+          conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 4)]));
+          conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 4)]));
+          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 12)]));
+          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 12)]));
+          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 12)]));
+          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 12)]));
+          conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 12)]));
+          conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 12)]));
+          conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 12)]));
+          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 20)]));
+          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 20)]));
+          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 20)]));
+          conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 20)]));
+          conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 20)]));
+          conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 20)]));
+          conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 20)]));
+          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 28)]));
+          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 28)]));
+          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 28)]));
+          conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 28)]));
+          conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 28)]));
+          conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 28)]));
+          conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 28)]));
+          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 5)]));
+          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 5)]));
+          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 5)]));
+          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 5)]));
+          conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 5)]));
+          conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 5)]));
+          conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 5)]));
+          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 13)]));
+          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 13)]));
+          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 13)]));
+          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 13)]));
+          conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 13)]));
+          conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 13)]));
+          conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 13)]));
+          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 21)]));
+          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 21)]));
+          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 21)]));
+          conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 21)]));
+          conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 21)]));
+          conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 21)]));
+          conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 21)]));
+          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 29)]));
+          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 29)]));
+          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 29)]));
+          conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 29)]));
+          conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 29)]));
+          conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 29)]));
+          conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 29)]));
+          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 294)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 6)]));
+          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 295)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 6)]));
+          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 296)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 6)]));
+          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 6)]));
+          conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 6)]));
+          conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 6)]));
+          conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 300)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 6)]));
+          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 294)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 14)]));
+          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 295)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 14)]));
+          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 296)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 14)]));
+          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 14)]));
+          conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 14)]));
+          conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 14)]));
+          conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 300)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 14)]));
+          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 294)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 22)]));
+          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 295)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 22)]));
+          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 296)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 22)]));
+          conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 22)]));
+          conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 22)]));
+          conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 22)]));
+          conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 300)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 22)]));
+          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 294)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 30)]));
+          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 295)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 30)]));
+          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 296)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 30)]));
+          conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 30)]));
+          conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 30)]));
+          conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 30)]));
+          conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 300)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 30)]));
+          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 7)]));
+          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 7)]));
+          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 7)]));
+          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 7)]));
+          conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 7)]));
+          conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 7)]));
+          conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 7)]));
+          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 15)]));
+          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 15)]));
+          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 15)]));
+          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 15)]));
+          conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 15)]));
+          conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 15)]));
+          conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 15)]));
+          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 23)]));
+          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 23)]));
+          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 23)]));
+          conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 23)]));
+          conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 23)]));
+          conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 23)]));
+          conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 23)]));
+          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 31)]));
+          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 31)]));
+          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 31)]));
+          conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 31)]));
+          conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 31)]));
+          conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 31)]));
+          conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 31)]));
         }
       }
-      for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
-        for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
-          compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
-        }
+      for (int i1_inner = 0; i1_inner < 4; ++i1_inner) {
+        compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
+        compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 1)] = max((conv2d_nchw[(i1_inner + 4)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
+        compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 2)] = max((conv2d_nchw[(i1_inner + 8)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
+        compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 3)] = max((conv2d_nchw[(i1_inner + 12)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
+        compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 4)] = max((conv2d_nchw[(i1_inner + 16)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
+        compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 5)] = max((conv2d_nchw[(i1_inner + 20)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
+        compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 6)] = max((conv2d_nchw[(i1_inner + 24)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
       }
     }
 
@@ -1377,7 +2039,7 @@ In the example below we resume the status and do more 5 trials.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 5 minutes  34.391 seconds)
+   **Total running time of the script:** ( 5 minutes  41.980 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 839d844126..e18030706c 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -643,7 +643,7 @@ so we can read the log file and load the best schedules.
     Evaluate inference time cost...
     Execution time summary:
      mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)  
-       7.8808       7.8798       7.8852       7.8775       0.0032   
+       7.8102       7.8081       7.8178       7.8047       0.0055   
                
 
 
@@ -671,7 +671,7 @@ Other Tips
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  3.847 seconds)
+   **Total running time of the script:** ( 1 minutes  2.943 seconds)
 
 
 .. _sphx_glr_download_how_to_tune_with_autoscheduler_tune_network_cuda.py:
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
index 753b04e6f4..4399d85d30 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
@@ -662,7 +662,7 @@ so we can read the log file and load the best schedules.
     Evaluate inference time cost...
     Execution time summary:
      mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)  
-      766.3268     766.0556     767.4808     765.4441      0.8533   
+      761.5435     761.6221     762.6183     760.3901      0.9114   
                
 
 
@@ -690,7 +690,7 @@ Other Tips
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  34.721 seconds)
+   **Total running time of the script:** ( 1 minutes  33.775 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 1ac1956243..28df8b4e4f 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
@@ -386,77 +386,77 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
                  placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [128, 512], []),
                  compute: Buffer(compute_2: Pointer(float32), float32, [128, 512], [])}
       buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute} {
-      for (i0.outer.i1.outer.fused: int32, 0, 256) "parallel" {
-        allocate(compute_3: Pointer(global float32), float32, [256]), storage_scope = global {
-          for (nb_j.inner: int32, 0, 2) {
-            for (i.inner.init: int32, 0, 8) {
-              let cse_var_1: int32 = ((i.inner.init*32) + (nb_j.inner*16))
-               {
-                compute_4: Buffer(compute_3, float32, [256], [])[cse_var_1] = 0f32
-                compute_4[(cse_var_1 + 1)] = 0f32
-                compute_4[(cse_var_1 + 2)] = 0f32
-                compute_4[(cse_var_1 + 3)] = 0f32
-                compute_4[(cse_var_1 + 4)] = 0f32
-                compute_4[(cse_var_1 + 5)] = 0f32
-                compute_4[(cse_var_1 + 6)] = 0f32
-                compute_4[(cse_var_1 + 7)] = 0f32
-                compute_4[(cse_var_1 + 8)] = 0f32
-                compute_4[(cse_var_1 + 9)] = 0f32
-                compute_4[(cse_var_1 + 10)] = 0f32
-                compute_4[(cse_var_1 + 11)] = 0f32
-                compute_4[(cse_var_1 + 12)] = 0f32
-                compute_4[(cse_var_1 + 13)] = 0f32
-                compute_4[(cse_var_1 + 14)] = 0f32
-                compute_4[(cse_var_1 + 15)] = 0f32
-              }
-            }
-            for (elem_idx: int32, 0, let cse_var_2: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_2 + 1)] - placeholder_15[cse_var_2])) {
-              for (i.inner: int32, 0, 8) {
-                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)*2048) + (i.inner*256))
-                let cse_var_17: int32 = (cse_var_20 + 9)
-                let cse_var_16: int32 = (cse_var_20 + 8)
-                let cse_var_15: int32 = (cse_var_20 + 7)
-                let cse_var_14: int32 = (cse_var_20 + 6)
-                let cse_var_13: int32 = (cse_var_20 + 5)
-                let cse_var_12: int32 = (cse_var_20 + 4)
-                let cse_var_11: int32 = (cse_var_20 + 3)
-                let cse_var_10: int32 = (cse_var_20 + 2)
-                let cse_var_9: int32 = (cse_var_20 + 15)
-                let cse_var_8: int32 = (cse_var_20 + 14)
-                let cse_var_7: int32 = (cse_var_20 + 13)
-                let cse_var_6: int32 = (cse_var_20 + 12)
-                let cse_var_5: int32 = (cse_var_20 + 11)
-                let cse_var_4: int32 = (cse_var_20 + 10)
-                let cse_var_3: int32 = (cse_var_20 + 1)
+      for (i0.outer.i1.outer.fused: int32, 0, 32) "parallel" {
+        allocate(compute_3: Pointer(global float32), float32, [2048]), storage_scope = global {
+          for (i.outer.inner: int32, 0, 2) {
+            for (nb_j.inner: int32, 0, 2) {
+              for (i.inner.init: int32, 0, 32) {
+                let cse_var_1: int32 = (((i.outer.inner*1024) + (i.inner.init*32)) + (nb_j.inner*16))
                  {
-                  compute_4[cse_var_20] = (compute_4[cse_var_20] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[((placeholder_15[cse_var_19]*16) + cse_var_21)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[(cse_var_18 + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_19] + elem_idx)])], 0f32)))
-                  compute_4[cse_var_3] = (compute_4[cse_var_3] + (placeholder_16[(((placeholder_15[cse_var_19]*16) + cse_var_21) + 1)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_19] + elem_idx)])], 0f32)))
-                  compute_4[cse_var_10] = (compute_4[cse_var_10] + (placeholder_16[(((placeholder_15[cse_var_19]*16) + cse_var_21) + 2)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_19] + elem_idx)])], 0f32)))
-                  compute_4[cse_var_11] = (compute_4[cse_var_11] + (placeholder_16[(((placeholder_15[cse_var_19]*16) + cse_var_21) + 3)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_19] + elem_idx)])], 0f32)))
-                  compute_4[cse_var_12] = (compute_4[cse_var_12] + (placeholder_16[(((placeholder_15[cse_var_19]*16) + cse_var_21) + 4)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_19] + elem_idx)])], 0f32)))
-                  compute_4[cse_var_13] = (compute_4[cse_var_13] + (placeholder_16[(((placeholder_15[cse_var_19]*16) + cse_var_21) + 5)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_19] + elem_idx)])], 0f32)))
-                  compute_4[cse_var_14] = (compute_4[cse_var_14] + (placeholder_16[(((placeholder_15[cse_var_19]*16) + cse_var_21) + 6)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_19] + elem_idx)])], 0f32)))
-                  compute_4[cse_var_15] = (compute_4[cse_var_15] + (placeholder_16[(((placeholder_15[cse_var_19]*16) + cse_var_21) + 7)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_19] + elem_idx)])], 0f32)))
-                  compute_4[cse_var_16] = (compute_4[cse_var_16] + (placeholder_16[(((placeholder_15[cse_var_19]*16) + cse_var_21) + 8)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_19] + elem_idx)])], 0f32)))
-                  compute_4[cse_var_17] = (compute_4[cse_var_17] + (placeholder_16[(((placeholder_15[cse_var_19]*16) + cse_var_21) + 9)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_19] + elem_idx)])], 0f32)))
-                  compute_4[cse_var_4] = (compute_4[cse_var_4] + (placeholder_16[(((placeholder_15[cse_var_19]*16) + cse_var_21) + 10)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_19] + elem_idx)])], 0f32)))
-                  compute_4[cse_var_5] = (compute_4[cse_var_5] + (placeholder_16[(((placeholder_15[cse_var_19]*16) + cse_var_21) + 11)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_19] + elem_idx)])], 0f32)))
-                  compute_4[cse_var_6] = (compute_4[cse_var_6] + (placeholder_16[(((placeholder_15[cse_var_19]*16) + cse_var_21) + 12)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_19] + elem_idx)])], 0f32)))
-                  compute_4[cse_var_7] = (compute_4[cse_var_7] + (placeholder_16[(((placeholder_15[cse_var_19]*16) + cse_var_21) + 13)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_19] + elem_idx)])], 0f32)))
-                  compute_4[cse_var_8] = (compute_4[cse_var_8] + (placeholder_16[(((placeholder_15[cse_var_19]*16) + cse_var_21) + 14)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_19] + elem_idx)])], 0f32)))
-                  compute_4[cse_var_9] = (compute_4[cse_var_9] + (placeholder_16[(((placeholder_15[cse_var_19]*16) + cse_var_21) + 15)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_19] + elem_idx)])], 0f32)))
+                  compute_4: Buffer(compute_3, float32, [2048], [])[cse_var_1] = 0f32
+                  compute_4[(cse_var_1 + 1)] = 0f32
+                  compute_4[(cse_var_1 + 2)] = 0f32
+                  compute_4[(cse_var_1 + 3)] = 0f32
+                  compute_4[(cse_var_1 + 4)] = 0f32
+                  compute_4[(cse_var_1 + 5)] = 0f32
+                  compute_4[(cse_var_1 + 6)] = 0f32
+                  compute_4[(cse_var_1 + 7)] = 0f32
+                  compute_4[(cse_var_1 + 8)] = 0f32
+                  compute_4[(cse_var_1 + 9)] = 0f32
+                  compute_4[(cse_var_1 + 10)] = 0f32
+                  compute_4[(cse_var_1 + 11)] = 0f32
+                  compute_4[(cse_var_1 + 12)] = 0f32
+                  compute_4[(cse_var_1 + 13)] = 0f32
+                  compute_4[(cse_var_1 + 14)] = 0f32
+                  compute_4[(cse_var_1 + 15)] = 0f32
+                }
+              }
+              for (elem_idx: int32, 0, let cse_var_2: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_2 + 1)] - placeholder_15[cse_var_2])) {
+                for (i.inner: int32, 0, 32) {
+                  let cse_var_21: int32 = (elem_idx*16)
+                  let cse_var_20: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
+                  let cse_var_19: int32 = (((i.outer.inner*1024) + (i.inner*32)) + (nb_j.inner*16))
+                  let cse_var_18: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i.outer.inner*8192)) + (i.inner*256))
+                  let cse_var_17: int32 = (cse_var_19 + 9)
+                  let cse_var_16: int32 = (cse_var_19 + 8)
+                  let cse_var_15: int32 = (cse_var_19 + 7)
+                  let cse_var_14: int32 = (cse_var_19 + 6)
+                  let cse_var_13: int32 = (cse_var_19 + 5)
+                  let cse_var_12: int32 = (cse_var_19 + 4)
+                  let cse_var_11: int32 = (cse_var_19 + 3)
+                  let cse_var_10: int32 = (cse_var_19 + 2)
+                  let cse_var_9: int32 = (cse_var_19 + 15)
+                  let cse_var_8: int32 = (cse_var_19 + 14)
+                  let cse_var_7: int32 = (cse_var_19 + 13)
+                  let cse_var_6: int32 = (cse_var_19 + 12)
+                  let cse_var_5: int32 = (cse_var_19 + 11)
+                  let cse_var_4: int32 = (cse_var_19 + 10)
+                  let cse_var_3: int32 = (cse_var_19 + 1)
+                   {
+                    compute_4[cse_var_19] = (compute_4[cse_var_19] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[((placeholder_15[cse_var_20]*16) + cse_var_21)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[(cse_var_18 + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_4[cse_var_3] = (compute_4[cse_var_3] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_4[cse_var_10] = (compute_4[cse_var_10] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_4[cse_var_11] = (compute_4[cse_var_11] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_4[cse_var_12] = (compute_4[cse_var_12] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_4[cse_var_13] = (compute_4[cse_var_13] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_4[cse_var_14] = (compute_4[cse_var_14] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_4[cse_var_15] = (compute_4[cse_var_15] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_4[cse_var_16] = (compute_4[cse_var_16] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_4[cse_var_17] = (compute_4[cse_var_17] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_4[cse_var_4] = (compute_4[cse_var_4] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_4[cse_var_5] = (compute_4[cse_var_5] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_4[cse_var_6] = (compute_4[cse_var_6] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_4[cse_var_7] = (compute_4[cse_var_7] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_4[cse_var_8] = (compute_4[cse_var_8] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_4[cse_var_9] = (compute_4[cse_var_9] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                  }
                 }
               }
             }
           }
-          for (i0.inner: int32, 0, 8) {
-            for (i1.inner: int32, 0, 32) {
-              let cse_var_22: int32 = ((((floordiv(i0.outer.i1.outer.fused, 16)*4096) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32)) + i1.inner)
-              compute_5: Buffer(compute_2, float32, [65536], [])[cse_var_22] = max((compute_4[((i0.inner*32) + i1.inner)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[cse_var_22]), 0f32)
-            }
+          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_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_22, 1, 32)] = max((compute_4[ramp((i0.inner*32), 1, 32)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
           }
         }
       }
@@ -512,7 +512,7 @@ We build the binary and check its correctness and performance.
 
  .. code-block:: none
 
-    Execution time of this operator: 1.909 ms
+    Execution time of this operator: 1.727 ms
 
 
 
diff --git a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
index 658dad9319..a49250e4ec 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
 
 Computation times
 =================
-**00:36.045** total execution time for **how_to_tune_with_autotvm** files:
+**01:12.272** 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``)           | 00:36.008 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)           | 01:12.236 | 0.0 MB |
 +--------------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)               | 00:00.022 | 0.0 MB |
 +--------------------------------------------------------------------------------------------------+-----------+--------+
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 d6c9bab549..5de7c4eb3c 100644
--- a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
@@ -387,25 +387,130 @@ for this template
       File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 64, 2, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7486054
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 4, 1, 128]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,496972
     No: 2   GFLOPS: 0.00/0.00       result: Traceback (most recent call last):
-      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
-        res = future.result()
-      File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
-        return self.__get_result()
-      File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
-        raise self._exception
-      File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
-        result = self.fn(*self.args, **self.kwargs)
-      File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
-        worker = lambda *args: self._worker_run(*args)
-      File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
-        return proc.recv()
-      File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
-        raise TimeoutError()
-    TimeoutError
-
-            [('tile_f', [-1, 1, 1, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7848555
+      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
+        func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
+        func = build(s, args, target_host=task.target_host, runtime=runtime)
+      File "/workspace/python/tvm/driver/build_module.py", line 227, in build
+        input_mod = lower(inputs, args, name=name, binds=binds)
+      File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
+        return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+      File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+      File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+      File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
+    tvm._ffi.base.TVMError: Traceback (most recent call last):
+      24: TVMFuncCall
+            at ../src/runtime/c_runtime_api.cc:477
+      23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+            at ../include/tvm/runtime/packed_func.h:1217
+      22: Call
+            at ../include/tvm/runtime/packed_func.h:1213
+      21: operator()
+            at ../include/tvm/runtime/packed_func.h:1730
+      20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+            at ../include/tvm/runtime/packed_func.h:1670
+      19: run<>
+            at ../include/tvm/runtime/packed_func.h:1630
+      18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1630
+      17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1630
+      16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1630
+      15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1630
+      14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1645
+      13: operator()
+            at ../src/driver/driver_api.cc:388
+      12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+            at ../src/driver/driver_api.cc:374
+      11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+            at ../src/driver/driver_api.cc:269
+      10: tvm::transform::Pass::operator()(tvm::IRModule) const
+            at ../src/ir/transform.cc:258
+      9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/ir/transform.cc:274
+      8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/ir/transform.cc:453
+      7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/ir/transform.cc:274
+      6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/tir/ir/transform.cc:100
+      5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+            at ../include/tvm/runtime/packed_func.h:1749
+      4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+            at ../include/tvm/runtime/packed_func.h:1693
+      3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+            at ../include/tvm/runtime/packed_func.h:1617
+      2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+            at ../include/tvm/runtime/packed_func.h:1217
+      1: Call
+            at ../include/tvm/runtime/packed_func.h:1213
+      0: operator()
+            at ../src/runtime/c_runtime_api.cc:534
+      File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+        raise InstantiationError("Skipped because of invalid gpu kernel")
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
+
+    Traceback (most recent call last):
+      24: TVMFuncCall
+            at ../src/runtime/c_runtime_api.cc:477
+      23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+            at ../include/tvm/runtime/packed_func.h:1217
+      22: Call
+            at ../include/tvm/runtime/packed_func.h:1213
+      21: operator()
+            at ../include/tvm/runtime/packed_func.h:1730
+      20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+            at ../include/tvm/runtime/packed_func.h:1670
+      19: run<>
+            at ../include/tvm/runtime/packed_func.h:1630
+      18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1630
+      17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1630
+      16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1630
+      15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1630
+      14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1645
+      13: operator()
+            at ../src/driver/driver_api.cc:388
+      12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+            at ../src/driver/driver_api.cc:374
+      11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+            at ../src/driver/driver_api.cc:269
+      10: tvm::transform::Pass::operator()(tvm::IRModule) const
+            at ../src/ir/transform.cc:258
+      9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/ir/transform.cc:274
+      8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/ir/transform.cc:453
+      7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/ir/transform.cc:274
+      6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/tir/ir/transform.cc:100
+      5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+            at ../include/tvm/runtime/packed_func.h:1749
+      4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+            at ../include/tvm/runtime/packed_func.h:1693
+      3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+            at ../include/tvm/runtime/packed_func.h:1617
+      2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+            at ../include/tvm/runtime/packed_func.h:1217
+      1: Call
+            at ../include/tvm/runtime/packed_func.h:1213
+      0: operator()
+            at ../src/runtime/c_runtime_api.cc:534
+      File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+        raise InstantiationError("Skipped because of invalid gpu kernel")
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 32, 2, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6896849
     No: 3   GFLOPS: 0.00/0.00       result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -528,7 +633,7 @@ for this template
       File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 4, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1143581
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 1, 4, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4347712
     No: 4   GFLOPS: 0.00/0.00       result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -651,7 +756,7 @@ for this template
       File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 2, 16, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1568686
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 16, 16, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8706369
     No: 5   GFLOPS: 0.00/0.00       result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -774,7 +879,7 @@ for this template
       File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 16, 32, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9896964
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 64, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5899526
     No: 6   GFLOPS: 0.00/0.00       result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -897,10 +1002,131 @@ for this template
       File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 4, 128, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,810091
-    No: 7   GFLOPS: 5.38/5.38       result: MeasureResult(costs=(0.043038143,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.510056734085083, timestamp=1670417483.1694725) [('tile_f', [-1, 1, 1, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,324555
-    No: 8   GFLOPS: 110.77/110.77   result: MeasureResult(costs=(0.0020900127083333334,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3307535648345947, timestamp=1670417483.8205762)      [('tile_f', [-1, 1, 2, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2169044
-    No: 9   GFLOPS: 0.00/110.77     result: Traceback (most recent call last):
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 1, 32, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4016261
+    No: 7   GFLOPS: 0.00/0.00       result: Traceback (most recent call last):
+      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
+        func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
+        func = build(s, args, target_host=task.target_host, runtime=runtime)
+      File "/workspace/python/tvm/driver/build_module.py", line 227, in build
+        input_mod = lower(inputs, args, name=name, binds=binds)
+      File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
+        return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+      File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+      File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+      File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
+    tvm._ffi.base.TVMError: Traceback (most recent call last):
+      24: TVMFuncCall
+            at ../src/runtime/c_runtime_api.cc:477
+      23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+            at ../include/tvm/runtime/packed_func.h:1217
+      22: Call
+            at ../include/tvm/runtime/packed_func.h:1213
+      21: operator()
+            at ../include/tvm/runtime/packed_func.h:1730
+      20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+            at ../include/tvm/runtime/packed_func.h:1670
+      19: run<>
+            at ../include/tvm/runtime/packed_func.h:1630
+      18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1630
+      17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1630
+      16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1630
+      15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1630
+      14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1645
+      13: operator()
+            at ../src/driver/driver_api.cc:388
+      12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+            at ../src/driver/driver_api.cc:374
+      11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+            at ../src/driver/driver_api.cc:269
+      10: tvm::transform::Pass::operator()(tvm::IRModule) const
+            at ../src/ir/transform.cc:258
+      9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/ir/transform.cc:274
+      8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/ir/transform.cc:453
+      7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/ir/transform.cc:274
+      6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/tir/ir/transform.cc:100
+      5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+            at ../include/tvm/runtime/packed_func.h:1749
+      4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+            at ../include/tvm/runtime/packed_func.h:1693
+      3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+            at ../include/tvm/runtime/packed_func.h:1617
+      2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+            at ../include/tvm/runtime/packed_func.h:1217
+      1: Call
+            at ../include/tvm/runtime/packed_func.h:1213
+      0: operator()
+            at ../src/runtime/c_runtime_api.cc:534
+      File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+        raise InstantiationError("Skipped because of invalid gpu kernel")
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
+
+    Traceback (most recent call last):
+      24: TVMFuncCall
+            at ../src/runtime/c_runtime_api.cc:477
+      23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+            at ../include/tvm/runtime/packed_func.h:1217
+      22: Call
+            at ../include/tvm/runtime/packed_func.h:1213
+      21: operator()
+            at ../include/tvm/runtime/packed_func.h:1730
+      20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+            at ../include/tvm/runtime/packed_func.h:1670
+      19: run<>
+            at ../include/tvm/runtime/packed_func.h:1630
+      18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1630
+      17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1630
+      16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1630
+      15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1630
+      14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1645
+      13: operator()
+            at ../src/driver/driver_api.cc:388
+      12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+            at ../src/driver/driver_api.cc:374
+      11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+            at ../src/driver/driver_api.cc:269
+      10: tvm::transform::Pass::operator()(tvm::IRModule) const
+            at ../src/ir/transform.cc:258
+      9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/ir/transform.cc:274
+      8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/ir/transform.cc:453
+      7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/ir/transform.cc:274
+      6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/tir/ir/transform.cc:100
+      5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+            at ../include/tvm/runtime/packed_func.h:1749
+      4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+            at ../include/tvm/runtime/packed_func.h:1693
+      3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+            at ../include/tvm/runtime/packed_func.h:1617
+      2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+            at ../include/tvm/runtime/packed_func.h:1217
+      1: Call
+            at ../include/tvm/runtime/packed_func.h:1213
+      0: operator()
+            at ../src/runtime/c_runtime_api.cc:534
+      File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+        raise InstantiationError("Skipped because of invalid gpu kernel")
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 1, 4, 128]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8959715
+    No: 8   GFLOPS: 0.00/0.00       result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1022,9 +1248,8 @@ for this template
       File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 16, 16, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10017078
-    No: 10  GFLOPS: 1.09/110.77     result: MeasureResult(costs=(0.212369934,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.9424479007720947, timestamp=1670417487.958273) [('tile_f', [-1, 16, 1, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2517188
-    No: 11  GFLOPS: 0.00/110.77     result: Traceback (most recent call last):
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 128, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3668746
+    No: 9   GFLOPS: 0.00/0.00       result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1146,8 +1371,8 @@ for this template
       File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 16, 2, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4441252
-    No: 12  GFLOPS: 0.00/110.77     result: Traceback (most recent call last):
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 2, 2, 64]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5789285
+    No: 10  GFLOPS: 0.00/0.00       result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1269,8 +1494,8 @@ for this template
       File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 8, 2, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6966446
-    No: 13  GFLOPS: 0.00/110.77     result: Traceback (most recent call last):
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 8, 32, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8429833
+    No: 11  GFLOPS: 0.00/0.00       result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1392,8 +1617,8 @@ for this template
       File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 1, 16, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6166414
-    No: 14  GFLOPS: 0.00/110.77     result: Traceback (most recent call last):
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 1, 128, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9456749
+    No: 12  GFLOPS: 0.00/0.00       result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1515,8 +1740,8 @@ for this template
       File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 8, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8626311
-    No: 15  GFLOPS: 0.00/110.77     result: Traceback (most recent call last):
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 32, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8886785
+    No: 13  GFLOPS: 0.00/0.00       result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1638,8 +1863,8 @@ for this template
       File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 2, 16, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3869079
-    No: 16  GFLOPS: 0.00/110.77     result: Traceback (most recent call last):
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 8, 4, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5921258
+    No: 14  GFLOPS: 0.00/0.00       result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1761,8 +1986,8 @@ for this template
       File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 4, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7136417
-    No: 17  GFLOPS: 0.00/110.77     result: Traceback (most recent call last):
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 2, 32, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1960111
+    No: 15  GFLOPS: 0.00/0.00       result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1884,8 +2109,8 @@ for this template
       File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 4, 4, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5218577
-    No: 18  GFLOPS: 0.00/110.77     result: Traceback (most recent call last):
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 1, 8, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1965854
+    No: 16  GFLOPS: 0.00/0.00       result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2007,8 +2232,9 @@ for this template
       File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 4, 1, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5559162
-    No: 19  GFLOPS: 0.00/110.77     result: Traceback (most recent call last):
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 16, 8, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,643625
+    No: 17  GFLOPS: 1.83/1.83       result: MeasureResult(costs=(0.126615013,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7828867435455322, timestamp=1670437283.4448225)        [('tile_f', [-1, 1, 1, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1396760
+    No: 18  GFLOPS: 0.00/1.83       result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2130,8 +2356,8 @@ for this template
       File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 32, 2, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3665533
-    No: 20  GFLOPS: 0.00/110.77     result: Traceback (most recent call last):
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 64, 4, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2739078
+    No: 19  GFLOPS: 0.00/1.83       result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2253,7 +2479,130 @@ for this template
       File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 2, 16, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2096906
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7349113
+    No: 20  GFLOPS: 0.00/1.83       result: Traceback (most recent call last):
+      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
+        func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
+        func = build(s, args, target_host=task.target_host, runtime=runtime)
+      File "/workspace/python/tvm/driver/build_module.py", line 227, in build
+        input_mod = lower(inputs, args, name=name, binds=binds)
+      File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
+        return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+      File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+      File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+      File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
+    tvm._ffi.base.TVMError: Traceback (most recent call last):
+      24: TVMFuncCall
+            at ../src/runtime/c_runtime_api.cc:477
+      23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+            at ../include/tvm/runtime/packed_func.h:1217
+      22: Call
+            at ../include/tvm/runtime/packed_func.h:1213
+      21: operator()
+            at ../include/tvm/runtime/packed_func.h:1730
+      20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+            at ../include/tvm/runtime/packed_func.h:1670
+      19: run<>
+            at ../include/tvm/runtime/packed_func.h:1630
+      18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1630
+      17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1630
+      16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1630
+      15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1630
+      14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1645
+      13: operator()
+            at ../src/driver/driver_api.cc:388
+      12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+            at ../src/driver/driver_api.cc:374
+      11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+            at ../src/driver/driver_api.cc:269
+      10: tvm::transform::Pass::operator()(tvm::IRModule) const
+            at ../src/ir/transform.cc:258
+      9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/ir/transform.cc:274
+      8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/ir/transform.cc:453
+      7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/ir/transform.cc:274
+      6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/tir/ir/transform.cc:100
+      5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+            at ../include/tvm/runtime/packed_func.h:1749
+      4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+            at ../include/tvm/runtime/packed_func.h:1693
+      3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+            at ../include/tvm/runtime/packed_func.h:1617
+      2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+            at ../include/tvm/runtime/packed_func.h:1217
+      1: Call
+            at ../include/tvm/runtime/packed_func.h:1213
+      0: operator()
+            at ../src/runtime/c_runtime_api.cc:534
+      File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+        raise InstantiationError("Skipped because of invalid gpu kernel")
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
+
+    Traceback (most recent call last):
+      24: TVMFuncCall
+            at ../src/runtime/c_runtime_api.cc:477
+      23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+            at ../include/tvm/runtime/packed_func.h:1217
+      22: Call
+            at ../include/tvm/runtime/packed_func.h:1213
+      21: operator()
+            at ../include/tvm/runtime/packed_func.h:1730
+      20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+            at ../include/tvm/runtime/packed_func.h:1670
+      19: run<>
+            at ../include/tvm/runtime/packed_func.h:1630
+      18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1630
+      17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1630
+      16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1630
+      15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1630
+      14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1645
+      13: operator()
+            at ../src/driver/driver_api.cc:388
+      12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+            at ../src/driver/driver_api.cc:374
+      11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+            at ../src/driver/driver_api.cc:269
+      10: tvm::transform::Pass::operator()(tvm::IRModule) const
+            at ../src/ir/transform.cc:258
+      9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/ir/transform.cc:274
+      8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/ir/transform.cc:453
+      7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/ir/transform.cc:274
+      6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/tir/ir/transform.cc:100
+      5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+            at ../include/tvm/runtime/packed_func.h:1749
+      4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+            at ../include/tvm/runtime/packed_func.h:1693
+      3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+            at ../include/tvm/runtime/packed_func.h:1617
+      2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+            at ../include/tvm/runtime/packed_func.h:1217
+      1: Call
+            at ../include/tvm/runtime/packed_func.h:1213
+      0: operator()
+            at ../src/runtime/c_runtime_api.cc:534
+      File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+        raise InstantiationError("Skipped because of invalid gpu kernel")
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 4, 2, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2538065
 
 
 
@@ -2308,12 +2657,17 @@ and measure running time.
     Finish loading 20 records
 
     Best config:
-    [('tile_f', [-1, 1, 2, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2169044
+    [('tile_f', [-1, 1, 1, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1396760
     Finish loading 20 records
-    Time cost of this operator: 0.002487
+    Time cost of this operator: 0.127007
+
+
+
 
 
+.. rst-class:: sphx-glr-timing
 
+   **Total running time of the script:** ( 1 minutes  12.236 seconds)
 
 
 .. _sphx_glr_download_how_to_tune_with_autotvm_tune_conv2d_cuda.py:
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 132e464c47..143be9b902 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
@@ -329,10 +329,10 @@ Timing the untuned program
     ########## Build without Autotuning ##########
     Node Name                                     Ops                                           Time(us)  Time(%)  Shape              Inputs  Outputs  Measurements(us)  
     ---------                                     ---                                           --------  -------  -----              ------  -------  ----------------  
-    tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  311.8     98.721   (1, 2, 10, 10, 3)  2       1        [311.8]           
-    tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       3.068     0.971    (1, 6, 10, 10)     1       1        [3.068]           
-    tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.973     0.308    (1, 1, 10, 10, 3)  1       1        [0.973]           
-    Total_time                                    -                                             315.841   -        -                  -       -        -                 
+    tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  308.9     98.713   (1, 2, 10, 10, 3)  2       1        [308.9]           
+    tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       3.049     0.974    (1, 6, 10, 10)     1       1        [3.049]           
+    tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.978     0.313    (1, 1, 10, 10, 3)  1       1        [0.978]           
+    Total_time                                    -                                             312.927   -        -                  -       -        -                 
 
 
 
@@ -397,10 +397,10 @@ Timing the tuned program
     ########## Build with Autotuning ##########
     Node Name                                     Ops                                           Time(us)  Time(%)  Shape              Inputs  Outputs  Measurements(us)  
     ---------                                     ---                                           --------  -------  -----              ------  -------  ----------------  
-    tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  102.6     97.431   (1, 6, 10, 10, 1)  2       1        [102.6]           
-    tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       1.806     1.715    (1, 6, 10, 10)     1       1        [1.806]           
-    tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.899     0.854    (1, 3, 10, 10, 1)  1       1        [0.899]           
-    Total_time                                    -                                             105.306   -        -                  -       -        -                 
+    tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  104.6     97.484   (1, 6, 10, 10, 1)  2       1        [104.6]           
+    tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       1.772     1.651    (1, 6, 10, 10)     1       1        [1.772]           
+    tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.929     0.865    (1, 3, 10, 10, 1)  1       1        [0.929]           
+    Total_time                                    -                                             107.3     -        -                  -       -        -                 
 
 
 
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
index 600be440ce..cd1c98c916 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
@@ -109,7 +109,7 @@ download a cat image and preprocess it to use as the model input.
     /venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/ao/quantization/utils.py:281: UserWarning: must run observer before calling calculate_qparams. Returning default values.
       "must run observer before calling calculate_qparams. " +
     Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
-
      0%|          | 0.00/3.42M [00:00<?, ?B/s]
     92%|#########2| 3.16M/3.42M [00:00<00:00, 33.2MB/s]
    100%|##########| 3.42M/3.42M [00:00<00:00, 35.3MB/s]
+
      0%|          | 0.00/3.42M [00:00<?, ?B/s]
    100%|##########| 3.42M/3.42M [00:00<00:00, 60.4MB/s]
     /workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
       return LooseVersion(torch_ver) > ver
     /venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -314,7 +314,7 @@ Look up prediction top 1 index in 1000 class synset.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  5.621 seconds)
+   **Total running time of the script:** ( 1 minutes  6.930 seconds)
 
 
 .. _sphx_glr_download_how_to_work_with_microtvm_micro_pytorch.py:
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
index 50db76f67a..75da0cd9e1 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/tmp0_hnp3bf/images/random'
+    '/tmp/tmp2ds93y81/images/random'
 
 
 
@@ -316,7 +316,7 @@ objects to other stuff? We can display some examples from our datasets using ``m
 
 
 .. image-sg:: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
-   :alt: [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0]
+   :alt: [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0]
    :srcset: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
    :class: sphx-glr-single-img
 
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
 
  .. code-block:: none
 
-    /tmp/tmp0_hnp3bf/images/target contains 8144 images
-    /tmp/tmp0_hnp3bf/images/random contains 5000 images
+    /tmp/tmp2ds93y81/images/target contains 8144 images
+    /tmp/tmp2ds93y81/images/random contains 5000 images
 
 
 
@@ -501,13 +501,13 @@ the time on our validation set).
  .. code-block:: none
 
     Epoch 1/3
-    328/328 - 47s - loss: 0.2188 - accuracy: 0.9246 - val_loss: 0.1096 - val_accuracy: 0.9615 - 47s/epoch - 144ms/step
+    328/328 - 48s - loss: 0.2211 - accuracy: 0.9244 - val_loss: 0.1686 - val_accuracy: 0.9471 - 48s/epoch - 146ms/step
     Epoch 2/3
-    328/328 - 44s - loss: 0.0977 - accuracy: 0.9656 - val_loss: 0.1007 - val_accuracy: 0.9634 - 44s/epoch - 133ms/step
+    328/328 - 44s - loss: 0.0972 - accuracy: 0.9629 - val_loss: 0.1509 - val_accuracy: 0.9494 - 44s/epoch - 133ms/step
     Epoch 3/3
-    328/328 - 43s - loss: 0.0615 - accuracy: 0.9754 - val_loss: 0.1930 - val_accuracy: 0.9407 - 43s/epoch - 132ms/step
+    328/328 - 43s - loss: 0.0732 - accuracy: 0.9720 - val_loss: 0.1112 - val_accuracy: 0.9634 - 43s/epoch - 133ms/step
 
-    <keras.callbacks.History object at 0x7fbf0f4b6ad0>
+    <keras.callbacks.History object at 0x7faf16f55c90>
 
 
 
@@ -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  51.632 seconds)
+   **Total running time of the script:** ( 4 minutes  48.393 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 d8bed6aa4a..9b1d45ef59 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
 
 Computation times
 =================
-**07:00.997** total execution time for **how_to_work_with_microtvm** files:
+**07:00.335** total execution time for **how_to_work_with_microtvm** files:
 
 +---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``)               | 04:51.632 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``)               | 04:48.393 | 0.0 MB |
 +---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``)           | 01:05.621 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``)           | 01:06.930 | 0.0 MB |
 +---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)         | 00:51.841 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)         | 00:52.473 | 0.0 MB |
 +---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``)                   | 00:08.011 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``)                   | 00:08.590 | 0.0 MB |
 +---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)             | 00:03.889 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)             | 00:03.946 | 0.0 MB |
 +---------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.py``) | 00:00.001 | 0.0 MB |
 +---------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index de1b0f7272..c952f34c93 100644
--- a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
 
 Computation times
 =================
-**00:45.683** total execution time for **how_to_work_with_relay** files:
+**00:45.258** total execution time for **how_to_work_with_relay** files:
 
 +----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:33.210 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:33.194 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)           | 00:10.878 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)           | 00:10.412 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)                             | 00:01.588 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)                             | 00:01.645 | 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 e85bc17701..40a8b61c1e 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 0x7fbf0af96c20>
+    <function my_cuda_math_rule at 0x7faf16a00c20>
 
 
 
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 344f6bea23..7361eb957e 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
 =================
-**00:08.287** total execution time for **how_to_work_with_schedules** files:
+**00:08.565** total execution time for **how_to_work_with_schedules** files:
 
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)                 | 00:05.744 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)                 | 00:05.996 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)                     | 00:01.163 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)                     | 00:01.193 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)                     | 00:00.590 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)                     | 00:00.589 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)                               | 00:00.570 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)                               | 00:00.568 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)                     | 00:00.116 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.052 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.051 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)                               | 00:00.029 | 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 f222bfa516..1da1426721 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -343,7 +343,7 @@ The importing needs to happen before the tensorized GEMV being executed.
                  B: Buffer(B_2: Pointer(float32), float32, [512, 64], []),
                  C: Buffer(C_2: Pointer(float32), float32, [1024, 512], [])}
       buffer_map = {A_1: A, B_1: B, C_1: C} {
-      attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp14058akj/input0.cc'\nsource_filename = \"/tmp/tmp14058akj/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/tmpyo6f510p/input0.cc'\nsource_filename = \"/tmp/tmpyo6f510p/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 762229b033..0ca106fe53 100644
--- a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
 
 Computation times
 =================
-**00:27.122** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:26.992** total execution time for **topic_vta_tutorials_autotvm** files:
 
 +---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:27.115 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:26.985 | 0.0 MB |
 +---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``)     | 00:00.007 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``)     | 00:00.006 | 0.0 MB |
 +---------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
index b7fecd88f2..44a58c3717 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -289,7 +289,7 @@ The compilation steps are:
       DeprecationWarning,
     /workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the  new recommended usage.
       relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
-    resnet18_v1 inference graph built in 30.51s!
+    resnet18_v1 inference graph built in 29.95s!
 
 
 
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 c4b7fdacbf..4d936779aa 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -333,7 +333,7 @@ The compilation steps are:
 
     /workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
       DeprecationWarning,
-    yolov3-tiny inference graph built in 20.69s!
+    yolov3-tiny inference graph built in 20.14s!
 
 
 
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 47c9e63109..413fe3f048 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
 =================
-**01:43.346** total execution time for **topic_vta_tutorials_frontend** files:
+**01:42.264** total execution time for **topic_vta_tutorials_frontend** files:
 
 +------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)           | 00:52.879 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)           | 00:52.327 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:50.467 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:49.936 | 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 7bd38dbb29..0d1a9b5fef 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
 =================
-**00:03.171** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.191** total execution time for **topic_vta_tutorials_optimize** files:
 
 +--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)         | 00:02.707 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)         | 00:02.733 | 0.0 MB |
 +--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.464 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.458 | 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 d6bfbe0d71..99515e90a4 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
 =================
-**00:00.814** total execution time for **topic_vta_tutorials** files:
+**00:00.836** total execution time for **topic_vta_tutorials** files:
 
 +---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.433 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.458 | 0.0 MB |
 +---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.381 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.378 | 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 b015e2529b..9b35707a84 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -207,8 +207,8 @@ trials, we can load the best schedule from the log file and apply it.
 
  .. code-block:: none
 
-    *E
 
+    *E
 
 
 
@@ -332,7 +332,7 @@ We build the binary and check its correctness and performance.
 
  .. code-block:: none
 
-    Execution time of this operator: 95.696 ms
+    Execution time of this operator: 94.765 ms
 
 
 
@@ -450,7 +450,7 @@ operations.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  25.636 seconds)
+   **Total running time of the script:** ( 1 minutes  29.127 seconds)
 
 
 .. _sphx_glr_download_tutorial_auto_scheduler_matmul_x86.py:
diff --git a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
index 5e065135c1..f6fdee3871 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -450,16 +450,16 @@ reduce variance, we take 5 measurements and average them.
     waiting for device...
     device available
     Get devices for measurement successfully!
-    No: 1   GFLOPS: 13.11/13.11     result: MeasureResult(costs=(0.0204709696,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.502300500869751, timestamp=1670415991.6460304)        [('tile_y', [-1, 8]), ('tile_x', [-1, 512])],None,93
-    No: 2   GFLOPS: 2.84/13.11      result: MeasureResult(costs=(0.0944459532,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7088754177093506, timestamp=1670415993.3666208)       [('tile_y', [-1, 2]), ('tile_x', [-1, 8])],None,31
-    No: 3   GFLOPS: 12.51/13.11     result: MeasureResult(costs=(0.0214650846,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5259785652160645, timestamp=1670415994.6706321)       [('tile_y', [-1, 128]), ('tile_x', [-1, 256])],None,87
-    No: 4   GFLOPS: 3.63/13.11      result: MeasureResult(costs=(0.0739154808,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3444387912750244, timestamp=1670415996.8239334)       [('tile_y', [-1, 16]), ('tile_x', [-1, 8])],None,34
-    No: 5   GFLOPS: 9.44/13.11      result: MeasureResult(costs=(0.028427039200000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6316802501678467, timestamp=1670415997.6703103)       [('tile_y', [-1, 8]), ('tile_x', [-1, 32])],None,53
-    No: 6   GFLOPS: 2.58/13.11      result: MeasureResult(costs=(0.1039415634,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.827890157699585, timestamp=1670415999.5000658)        [('tile_y', [-1, 8]), ('tile_x', [-1, 4])],None,23
-    No: 7   GFLOPS: 2.77/13.11      result: MeasureResult(costs=(0.096935432,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7134826183319092, timestamp=1670416002.0104043)        [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
-    No: 8   GFLOPS: 9.75/13.11      result: MeasureResult(costs=(0.0275318876,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7504794597625732, timestamp=1670416002.6633904)       [('tile_y', [-1, 8]), ('tile_x', [-1, 128])],None,73
-    No: 9   GFLOPS: 2.26/13.11      result: MeasureResult(costs=(0.1187354182,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0223867893218994, timestamp=1670416004.815486)        [('tile_y', [-1, 4]), ('tile_x', [-1, 2])],None,12
-    No: 10  GFLOPS: 11.27/13.11     result: MeasureResult(costs=(0.0238221966,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5125246047973633, timestamp=1670416005.3633463)       [('tile_y', [-1, 128]), ('tile_x', [-1, 32])],None,57
+    No: 1   GFLOPS: 9.62/9.62       result: MeasureResult(costs=(0.027909457200000005,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6171848773956299, timestamp=1670435794.624019)        [('tile_y', [-1, 4]), ('tile_x', [-1, 32])],None,52
+    No: 2   GFLOPS: 11.20/11.20     result: MeasureResult(costs=(0.0239746986,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5711414813995361, timestamp=1670435795.2168183)       [('tile_y', [-1, 256]), ('tile_x', [-1, 512])],None,98
+    No: 3   GFLOPS: 12.60/12.60     result: MeasureResult(costs=(0.0213061344,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5946743488311768, timestamp=1670435796.5378685)       [('tile_y', [-1, 64]), ('tile_x', [-1, 128])],None,76
+    No: 4   GFLOPS: 8.62/12.60      result: MeasureResult(costs=(0.031157626,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6299936771392822, timestamp=1670435798.0143173)        [('tile_y', [-1, 512]), ('tile_x', [-1, 256])],None,89
+    No: 5   GFLOPS: 10.53/12.60     result: MeasureResult(costs=(0.025492876799999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5626485347747803, timestamp=1670435798.7832034)       [('tile_y', [-1, 256]), ('tile_x', [-1, 32])],None,58
+    No: 6   GFLOPS: 3.31/12.60      result: MeasureResult(costs=(0.0811695088,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4563641548156738, timestamp=1670435800.2529602)       [('tile_y', [-1, 8]), ('tile_x', [-1, 8])],None,33
+    No: 7   GFLOPS: 11.49/12.60     result: MeasureResult(costs=(0.023368445199999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6284217834472656, timestamp=1670435801.6079597)       [('tile_y', [-1, 256]), ('tile_x', [-1, 128])],None,78
+    No: 8   GFLOPS: 1.80/12.60      result: MeasureResult(costs=(0.14953502840000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5785422325134277, timestamp=1670435804.2114093)        [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+    No: 9   GFLOPS: 10.11/12.60     result: MeasureResult(costs=(0.0265444944,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5645365715026855, timestamp=1670435804.8896155)       [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+    No: 10  GFLOPS: 0.50/12.60      result: MeasureResult(costs=(0.5382590142,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.728872299194336, timestamp=1670435813.667946) [('tile_y', [-1, 32]), ('tile_x', [-1, 1])],None,5
 
 
 
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 37c0fb0a8c..8e3b2f371b 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -320,7 +320,7 @@ standard deviation.
 
  .. code-block:: none
 
-    {'mean': 520.4171909400009, 'median': 521.4053322000041, 'std': 2.5748459860689517}
+    {'mean': 519.6498904799989, 'median': 519.5562873500023, 'std': 3.6570841684229767}
 
 
 
@@ -554,31 +554,29 @@ the tuning data to.
 
  .. code-block:: none
 
-
    [Task  1/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  1/25]  Current/Best:   23.03/  23.03 GFLOPS | Progress: (4/20) | 8.52 s
    [Task  1/25]  Current/Best:    8.78/  23.03 GFLOPS | Progress: (8/20) | 11.57 s
    [Task  1/25]  Current/Best:    6.35/  23.03 GFLOPS | Progress: (12/20) | 14.17 s
    [Task  1/25]  Current/Best:   15.55/  23.03 GFLOPS | Progress: (16/20) | 17.68 s
    [Task  1/25]  Current/Best:   14.91/  23.03 GFLOPS | Progress: (20/20) | 21.16 s Done.
-
    [Task  2/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  2/25]  Current/Best:   19.79/  19.79 GFLOPS | Progress: (4/20) | 2.81 s
    [Task  2/25]  Current/Best:    6.74/  19.79 GFLOPS | Progress: (8/20) | 4.16 s
    [Task  2/25]  Current/Best:   15.19/  19.79 GFLOPS | Progress: (12/20) | 5.21 s
    [Task  2/25]  Current/Best:    5.60/  22.59 GFLOPS | Progress: (16/20) | 6.34 s
    [Task  2/25]  Current/Best:   15.26/  22.59 GFLOPS | Progress: (20/20) | 7.93 s Done.
-
    [Task  3/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  3/25]  Current/Best:   13.55/  20.09 GFLOPS | Progress: (4/20) | 3.64 s
    [Task  3/25]  Current/Best:   17.69/  20.09 GFLOPS | Progress: (8/20) | 5.60 s
    [Task  3/25]  Current/Best:    7.92/  20.09 GFLOPS | Progress: (12/20) | 8.24 s
    [Task  3/25]  Current/Best:   18.34/  20.09 GFLOPS | Progress: (16/20) | 10.06 s
    [Task  3/25]  Current/Best:    7.36/  20.09 GFLOPS | Progress: (20/20) | 12.14 s Done.
-
    [Task  4/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  4/25]  Current/Best:   20.55/  20.55 GFLOPS | Progress: (4/20) | 12.45 s
    [Task  4/25]  Current/Best:   13.15/  20.55 GFLOPS | Progress: (8/20) | 15.26 s
    [Task  4/25]  Current/Best:    6.81/  20.55 GFLOPS | Progress: (12/20) | 16.78 s
    [Task  4/25]  Current/Best:    2.24/  20.55 GFLOPS | Progress: (16/20) | 18.59 s
    [Task  4/25]  Current/Best:    6.64/  20.55 GFLOPS | Progress: (20/20) | 20.42 s Done.
-
    [Task  5/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  5/25]  Current/Best:    7.28/  14.68 GFLOPS | Progress: (4/20) | 4.36 s
    [Task  5/25]  Current/Best:    3.98/  14.73 GFLOPS | Progress: (8/20) | 6.77 s
    [Task  5/25]  Current/Best:   19.89/  22.79 GFLOPS | Progress: (12/20) | 8.61 s
    [Task  5/25]  Current/Best:    9.97/  22.79 GFLOPS | Progress: (16/20) | 10.37 s
    [Task  5/25]  Current/Best:   11.73/  22.79 GFLOPS | Progress: (20/20) | 12.74 s Done.
-
    [Task  6/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  6/25]  Current/Best:   20.45/  20.45 GFLOPS | Progress: (4/20) | 3.56 s
    [Task  6/25]  Current/Best:   17.26/  20.45 GFLOPS | Progress: (8/20) | 6.15 s
    [Task  6/25]  Current/Best:    5.05/  20.45 GFLOPS | Progress: (12/20) | 8.95 s
    [Task  6/25]  Current/Best:   11.79/  20.45 GFLOPS | Progress: (16/20) | 15.00 s
    [Task  6/25]  Current/Best:    9.96/  20.45 GFLOPS | Progress: (20/20) | 20.27 s Done.
-
    [Task  7/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  7/25]  Current/Best:    5.46/  18.86 GFLOPS | Progress: (4/20) | 3.58 s
    [Task  7/25]  Current/Best:   12.87/  18.86 GFLOPS | Progress: (8/20) | 5.64 s
    [Task  7/25]  Current/Best:   14.95/  18.86 GFLOPS | Progress: (12/20) | 7.58 s
    [Task  7/25]  Current/Best:   14.54/  19.85 GFLOPS | Progress: (16/20) | 9.32 s
    [Task  7/25]  Current/Best:   10.22/  23.07 GFLOPS | Progress: (20/20) | 11.32 s Done.
-
    [Task  8/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  8/25]  Current/Best:    9.62/  13.23 GFLOPS | Progress: (4/20) | 5.23 s
    [Task  8/25]  Current/Best:   17.47/  17.47 GFLOPS | Progress: (8/20) | 10.86 s
    [Task  8/25]  Current/Best:   14.19/  17.47 GFLOPS | Progress: (12/20) | 15.38 s
    [Task  8/25]  Current/Best:   10.85/  17.47 GFLOPS | Progress: (16/20) | 24.14 s
    [Task  8/25]  Current/Best:   10.80/  17.47 GFLOPS | Progress: (20/20) | 26.05 s Done.
-
    [Task  9/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  9/25]  Current/Best:   17.18/  20.54 GFLOPS | Progress: (4/20) | 2.82 s
    [Task  9/25]  Current/Best:   13.26/  20.54 GFLOPS | Progress: (8/20) | 7.58 s
    [Task  9/25]  Current/Best:   22.09/  22.09 GFLOPS | Progress: (12/20) | 18.54 s
    [Task  9/25]  Current/Best:   10.96/  23.13 GFLOPS | Progress: (16/20) | 23.52 s
    [Task  9/25]  Current/Best:   18.18/  23.13 GFLOPS | Progress: (20/20) | 24.79 s
    [Task 10/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 10/25]  Current/Best:    9.95/  14.50 GFLOPS | Progress: (4/20) | 4.31 s
    [Task 10/25]  Current/Best:    5.19/  14.50 GFLOPS | Progress: (8/20) | 7.40 s
    [Task 10/25]  Current/Best:    9.03/  14.80 GFLOPS | Progress: (12/20) | 9.37 s
    [Task 10/25]  Current/Best:   10.87/  15.40 GFLOPS | Progress: (16/20) | 11.46 s
    [Task 10/25]  Current/Best:   18.86/  20.15 GFLOPS | Progress: (20/20)
  | 12.84 s Done.
-
    [Task 11/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 11/25]  Current/Best:    1.58/  16.49 GFLOPS | Progress: (4/20) | 5.44 s
    [Task 11/25]  Current/Best:   16.62/  21.63 GFLOPS | Progress: (8/20) | 7.56 s
    [Task 11/25]  Current/Best:    7.48/  21.63 GFLOPS | Progress: (12/20) | 10.72 s
    [Task 11/25]  Current/Best:   14.60/  21.63 GFLOPS | Progress: (16/20) | 12.72 s
    [Task 11/25]  Current/Best:   14.82/  21.63 GFLOPS | Progress: (20/20) | 15.07 s Done.
-
    [Task 12/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 12/25]  Current/Best:    6.08/  21.15 GFLOPS | Progress: (4/20) | 6.72 s
    [Task 12/25]  Current/Best:   18.37/  21.15 GFLOPS | Progress: (8/20) | 10.92 s
    [Task 12/25]  Current/Best:   11.53/  21.15 GFLOPS | Progress: (12/20) | 14.95 s
    [Task 12/25]  Current/Best:    4.61/  21.15 GFLOPS | Progress: (16/20) | 16.95 s
    [Task 12/25]  Current/Best:   10.32/  21.15 GFLOPS | Progress: (20/20) | 19.53 s Done.
-
    [Task 13/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 13/25]  Current/Best:   18.95/  18.95 GFLOPS | Progress: (4/20) | 4.49 s
    [Task 13/25]  Current/Best:   11.97/  18.95 GFLOPS | Progress: (8/20) | 6.89 s
    [Task 13/25]  Current/Best:    9.64/  21.41 GFLOPS | Progress: (12/20) | 9.23 s
    [Task 13/25]  Current/Best:   11.16/  21.41 GFLOPS | Progress: (16/20) | 12.93 s
    [Task 13/25]  Current/Best:   11.43/  21.41 GFLOPS | Progress: (20/20) | 14.84 s Done.
-
    [Task 14/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 14/25]  Current/Best:   19.61/  21.47 GFLOPS | Progress: (4/20) | 3.17 s
    [Task 14/25]  Current/Best:   14.04/  21.47 GFLOPS | Progress: (8/20) | 7.71 s
    [Task 14/25]  Current/Best:   14.68/  21.47 GFLOPS | Progress: (12/20) | 11.47 s
    [Task 14/25]  Current/Best:   21.24/  21.47 GFLOPS | Progress: (16/20) | 13.10 s
    [Task 14/25]  Current/Best:    2.83/  21.47 GFLOPS | Progress: (20/20) | 19.91 s Done.
-
    [Task 15/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 15/25]  Current/Best:   18.25/  20.23 GFLOPS | Progress: (4/20) | 2.86 s
    [Task 15/25]  Current/Best:   18.66/  20.23 GFLOPS | Progress: (8/20) | 4.71 s
    [Task 15/25]  Current/Best:    6.09/  20.23 GFLOPS | Progress: (12/20) | 6.88 s
    [Task 15/25]  Current/Best:    3.10/  20.23 GFLOPS | Progress: (16/20) | 9.90 s
    [Task 15/25]  Current/Best:    3.17/  20.23 GFLOPS | Progress: (20/20) | 12.58 s
    [Task 16/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
-     Done.
-
    [Task 16/25]  Current/Best:   12.54/  21.09 GFLOPS | Progress: (4/20) | 2.78 s
    [Task 16/25]  Current/Best:    9.00/  21.09 GFLOPS | Progress: (8/20) | 4.96 s
    [Task 16/25]  Current/Best:   14.57/  21.09 GFLOPS | Progress: (12/20) | 6.37 s
    [Task 16/25]  Current/Best:    4.97/  21.09 GFLOPS | Progress: (16/20) | 7.77 s
    [Task 16/25]  Current/Best:   11.74/  21.09 GFLOPS | Progress: (20/20) | 9.31 s Done.
-
    [Task 17/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 17/25]  Current/Best:   17.83/  22.16 GFLOPS | Progress: (4/20) | 4.70 s
    [Task 17/25]  Current/Best:   16.33/  22.16 GFLOPS | Progress: (8/20) | 6.96 s
    [Task 17/25]  Current/Best:   12.14/  22.16 GFLOPS | Progress: (12/20) | 9.17 s
    [Task 17/25]  Current/Best:    3.09/  22.16 GFLOPS | Progress: (16/20) | 12.03 s
    [Task 17/25]  Current/Best:    3.10/  22.16 GFLOPS | Progress: (20/20) | 15.14 s Done.
-
    [Task 18/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 18/25]  Current/Best:    4.25/  14.49 GFLOPS | Progress: (4/20) | 5.23 s
    [Task 18/25]  Current/Best:   17.87/  17.87 GFLOPS | Progress: (8/20) | 8.93 s
    [Task 18/25]  Current/Best:   14.17/  17.87 GFLOPS | Progress: (12/20) | 10.98 s
    [Task 18/25]  Current/Best:   12.11/  22.57 GFLOPS | Progress: (16/20) | 14.43 s
    [Task 18/25]  Current/Best:   15.14/  22.57 GFLOPS | Progress: (20/20) | 16.75 s Done.
-
    [Task 19/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 19/25]  Current/Best:   16.57/  19.44 GFLOPS | Progress: (4/20) | 4.52 s
    [Task 19/25]  Current/Best:   17.49/  19.44 GFLOPS | Progress: (8/20) | 7.28 s
    [Task 19/25]  Current/Best:   10.95/  19.44 GFLOPS | Progress: (12/20) | 10.00 s
    [Task 19/25]  Current/Best:    8.45/  19.44 GFLOPS | Progress: (16/20) | 13.79 s
    [Task 19/25]  Current/Best:   11.96/  19.44 GFLOPS | Progress: (20/20) | 17.62 s Done.
-
    [Task 20/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 20/25]  Current/Best:   14.91/  18.43 GFLOPS | Progress: (4/20) | 3.26 s
    [Task 20/25]  Current/Best:    2.61/  18.43 GFLOPS | Progress: (8/20) | 6.75 s
    [Task 20/25]  Current/Best:   16.39/  18.43 GFLOPS | Progress: (12/20) | 9.15 s
    [Task 20/25]  Current/Best:   20.24/  20.24 GFLOPS | Progress: (16/20) | 11.09 s
    [Task 20/25]  Current/Best:   13.25/  20.24 GFLOPS | Progress: (20/20) | 13.80 s
    [Task 21/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 21/25]  Current/Best:   20.49/  20.49 GFLOPS | Progress: (4/20) | 4.10 s
    [Task 21/25]  Current/Best:   16.23/  20.49 GFLOPS | Progress: (8/20) | 7.36 s Done.
-
    [Task 21/25]  Current/Best:    9.15/  20.49 GFLOPS | Progress: (12/20) | 9.14 s
    [Task 21/25]  Current/Best:    3.15/  20.49 GFLOPS | Progress: (16/20) | 10.77 s
    [Task 21/25]  Current/Best:   10.52/  20.49 GFLOPS | Progress: (20/20) | 13.25 s
    [Task 22/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 22/25]  Current/Best:   20.26/  21.73 GFLOPS | Progress: (4/20) | 4.49 s
    [Task 22/25]  Current/Best:    8.39/  21.73 GFLOPS | Progress: (8/20) | 6.52 s
    [Task 22/25]  Current/Best:   14.52/  21.73 GFLOPS | Progress: (12/20) | 8.02 s
    [Task 22/25]  Current/Best:   13.11/  21.73 GFLOPS | Progress: (16/20) | 9.36 s
    [Task 22/25]  Current/Best:   11.79/  21.73 GFLOPS | Progress: (20/20) | 11.01 s Done.
-
    [Task 23/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 23/25]  Current/Best:   22.20/  22.20 GFLOPS | Progress: (4/20) | 4.80 s
    [Task 23/25]  Current/Best:    5.29/  22.20 GFLOPS | Progress: (8/20) | 7.39 s
    [Task 23/25]  Current/Best:   12.86/  22.20 GFLOPS | Progress: (12/20) | 12.04 s
    [Task 23/25]  Current/Best:   10.54/  22.20 GFLOPS | Progress: (16/20) | 15.43 s
    [Task 23/25]  Current/Best:   17.06/  22.20 GFLOPS | Progress: (20/20) | 17.67 s Done.
-
    [Task 24/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 24/25]  Current/Best:    7.82/   7.82 GFLOPS | Progress: (4/20) | 12.13 s
    [Task 24/25]  Current/Best:    6.83/   7.82 GFLOPS | Progress: (8/20) | 22.87 s
    [Task 24/25]  Current/Best:    4.48/   7.82 GFLOPS | Progress: (12/20) | 25.98 s
    [Task 24/25]  Current/Best:    5.60/   8.85 GFLOPS | Progress: (16/20) | 27.06 s
    [Task 24/25]  Current/Best:    7.23/   8.85 GFLOPS | Progress: (20/20) | 37.33 s
    [Task 25/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
-     Done.
-
    [Task 25/25]  Current/Best:    8.08/   8.72 GFLOPS | Progress: (4/20) | 5.10 s
    [Task 25/25]  Current/Best:    8.74/   8.74 GFLOPS | Progress: (8/20) | 15.86 s
    [Task 25/25]  Current/Best:    8.54/   8.74 GFLOPS | Progress: (12/20) | 26.58 s
    [Task 25/25]  Current/Best:    3.39/   8.74 GFLOPS | Progress: (16/20) | 37.09 s
    [Task 25/25]  Current/Best:    8.82/   8.82 GFLOPS | Progress: (20/20) | 48.66 s
+
    [Task  1/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  1/25]  Current/Best:   17.58/  19.05 GFLOPS | Progress: (4/20) | 8.39 s
    [Task  1/25]  Current/Best:   11.09/  19.05 GFLOPS | Progress: (8/20) | 12.81 s
    [Task  1/25]  Current/Best:   22.91/  22.91 GFLOPS | Progress: (12/20) | 15.09 s
    [Task  1/25]  Current/Best:   21.14/  23.46 GFLOPS | Progress: (16/20) | 17.70 s
    [Task  1/25]  Current/Best:    7.35/  23.46 GFLOPS | Progress: (20/20) | 20.82 s Done.
+
    [Task  2/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  2/25]  Current/Best:    8.91/  15.21 GFLOPS | Progress: (4/20) | 3.23 s
    [Task  2/25]  Current/Best:   10.23/  15.21 GFLOPS | Progress: (8/20) | 4.98 s
    [Task  2/25]  Current/Best:    4.77/  16.62 GFLOPS | Progress: (12/20) | 6.33 s
    [Task  2/25]  Current/Best:   13.06/  22.13 GFLOPS | Progress: (16/20) | 7.62 s
    [Task  2/25]  Current/Best:    3.75/  22.13 GFLOPS | Progress: (20/20) | 9.09 s Done.
+
    [Task  3/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  3/25]  Current/Best:   17.23/  22.26 GFLOPS | Progress: (4/20) | 3.86 s
    [Task  3/25]  Current/Best:    6.15/  22.26 GFLOPS | Progress: (8/20) | 6.27 s
    [Task  3/25]  Current/Best:   24.02/  24.02 GFLOPS | Progress: (12/20) | 7.89 s
    [Task  3/25]  Current/Best:   18.16/  24.02 GFLOPS | Progress: (16/20) | 10.29 s
    [Task  3/25]  Current/Best:    6.38/  24.02 GFLOPS | Progress: (20/20) | 12.36 s Done.
+
    [Task  4/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  4/25]  Current/Best:   10.41/  16.11 GFLOPS | Progress: (4/20) | 3.60 s
    [Task  4/25]  Current/Best:    6.40/  16.70 GFLOPS | Progress: (8/20) | 8.45 s
    [Task  4/25]  Current/Best:   13.76/  16.70 GFLOPS | Progress: (12/20) | 11.28 s
    [Task  4/25]  Current/Best:    9.34/  21.20 GFLOPS | Progress: (16/20) | 17.81 s
    [Task  4/25]  Current/Best:   11.23/  22.79 GFLOPS | Progress: (20/20) | 19.27 s Done.
+
    [Task  5/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  5/25]  Current/Best:   12.20/  17.63 GFLOPS | Progress: (4/20) | 3.13 s
    [Task  5/25]  Current/Best:   11.48/  17.63 GFLOPS | Progress: (8/20) | 5.04 s
    [Task  5/25]  Current/Best:    9.89/  17.63 GFLOPS | Progress: (12/20) | 7.12 s
    [Task  5/25]  Current/Best:   10.42/  21.15 GFLOPS | Progress: (16/20) | 8.84 s
    [Task  5/25]  Current/Best:    8.45/  21.15 GFLOPS | Progress: (20/20) | 11.24 s Done.
+
    [Task  6/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  6/25]  Current/Best:    8.99/  18.23 GFLOPS | Progress: (4/20) | 4.43 s
    [Task  6/25]  Current/Best:   23.22/  23.22 GFLOPS | Progress: (8/20) | 6.73 s
    [Task  6/25]  Current/Best:   13.17/  23.22 GFLOPS | Progress: (12/20) | 8.52 s
    [Task  6/25]  Current/Best:   19.19/  23.22 GFLOPS | Progress: (16/20) | 11.64 s
    [Task  6/25]  Current/Best:   11.57/  23.22 GFLOPS | Progress: (20/20) | 14.26 s Done.
+
    [Task  7/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  7/25]  Current/Best:    5.76/  19.97 GFLOPS | Progress: (4/20) | 3.62 s
    [Task  7/25]  Current/Best:   12.61/  19.97 GFLOPS | Progress: (8/20) | 6.31 s
    [Task  7/25]  Current/Best:   11.74/  19.97 GFLOPS | Progress: (12/20) | 9.26 s
    [Task  7/25]  Current/Best:   19.70/  22.74 GFLOPS | Progress: (16/20) | 11.62 s
    [Task  7/25]  Current/Best:   20.11/  22.74 GFLOPS | Progress: (20/20) | 13.65 s Done.
+
    [Task  8/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  8/25]  Current/Best:   10.13/  11.31 GFLOPS | Progress: (4/20) | 7.36 s
    [Task  8/25]  Current/Best:   15.60/  15.60 GFLOPS | Progress: (8/20) | 12.83 s
    [Task  8/25]  Current/Best:    8.73/  15.60 GFLOPS | Progress: (12/20) | 21.35 s
    [Task  8/25]  Current/Best:   16.78/  16.78 GFLOPS | Progress: (16/20) | 27.78 s
    [Task  8/25]  Current/Best:   14.41/  16.78 GFLOPS | Progress: (20/20) | 37.68 s Done.
+
    [Task  9/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  9/25]  Current/Best:    8.17/  18.68 GFLOPS | Progress: (4/20) | 4.77 s
    [Task  9/25]  Current/Best:   22.38/  22.38 GFLOPS | Progress: (8/20) | 6.58 s
    [Task  9/25]  Current/Best:   18.55/  22.38 GFLOPS | Progress: (12/20) | 11.57 s
    [Task  9/25]  Current/Best:   20.95/  22.38 GFLOPS | Progress: (16/20) | 12.76 s
    [Task  9/25]  Current/Best:    4.76/  22.38 GFLOPS | Progress: (20/20) | 20.50 s Done.
+
    [Task 10/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 10/25]  Current/Best:    5.26/  18.57 GFLOPS | Progress: (4/20) | 3.01 s
    [Task 10/25]  Current/Best:    3.13/  18.57 GFLOPS | Progress: (8/20) | 5.46 s
    [Task 10/25]  Current/Best:   10.17/  18.57 GFLOPS | Progress: (12/20) | 7.20 s
    [Task 10/25]  Current/Best:   19.86/  19.86 GFLOPS | Progress: (16/20) | 9.21 s
    [Task 10/25]  Current/Best:   17.46/  20.17 GFLOPS | Progress: (20/20) | 10.67 s Done.
+
    [Task 11/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 11/25]  Current/Best:    6.89/  18.66 GFLOPS | Progress: (4/20) | 4.30 s
    [Task 11/25]  Current/Best:   13.06/  18.79 GFLOPS | Progress: (8/20) | 6.67 s
    [Task 11/25]  Current/Best:   11.91/  18.79 GFLOPS | Progress: (12/20) | 9.19 s
    [Task 11/25]  Current/Best:    7.17/  22.20 GFLOPS | Progress: (16/20) | 11.50 s
    [Task 11/25]  Current/Best:   18.16/  22.20 GFLOPS | Progress: (20/20) | 14.21 s Done.
+
    [Task 12/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 12/25]  Current/Best:   17.13/  17.13 GFLOPS | Progress: (4/20) | 6.30 s
    [Task 12/25]  Current/Best:   10.32/  17.13 GFLOPS | Progress: (8/20) | 12.79 s
    [Task 12/25]  Current/Best:    9.39/  17.13 GFLOPS | Progress: (12/20) | 14.68 s
    [Task 12/25]  Current/Best:    5.33/  17.13 GFLOPS | Progress: (16/20) | 18.09 s
    [Task 12/25]  Current/Best:   12.83/  17.13 GFLOPS | Progress: (20/20) | 22.64 s Done.
+
    [Task 13/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 13/25]  Current/Best:   18.72/  18.72 GFLOPS | Progress: (4/20) | 3.37 s
    [Task 13/25]  Current/Best:    4.04/  21.96 GFLOPS | Progress: (8/20) | 5.61 s
    [Task 13/25]  Current/Best:   11.70/  21.96 GFLOPS | Progress: (12/20) | 8.42 s
    [Task 13/25]  Current/Best:   12.09/  21.96 GFLOPS | Progress: (16/20) | 11.69 s
    [Task 13/25]  Current/Best:   12.01/  21.96 GFLOPS | Progress: (20/20) | 14.75 s Done.
+
    [Task 14/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 14/25]  Current/Best:   13.22/  15.93 GFLOPS | Progress: (4/20) | 6.97 s
    [Task 14/25]  Current/Best:    4.45/  15.93 GFLOPS | Progress: (8/20) | 10.24 s
    [Task 14/25]  Current/Best:    3.65/  15.93 GFLOPS | Progress: (12/20) | 15.66 s
    [Task 14/25]  Current/Best:    8.03/  18.91 GFLOPS | Progress: (16/20) | 19.83 s
    [Task 14/25]  Current/Best:   11.51/  18.91 GFLOPS | Progress: (20/20) | 22.48 s
    [Task 15/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 15/25]  Current/Best:   12.60/  19.04 GFLOPS | Progress: (4/20) | 6.18 s
    [Task 15/25]  Current/Best:    5.62/  19.04 GFLOPS | Progress: (8/20) | 7.76 s
    [Task 15/25]  Current/Best:   14.29/  19.04 GFLOPS | Progress: (12/20) | 9.61 s
    [Task 15/25]  Current/Best:   10.84/  21.01 GFLOPS | Progress: (16/20) | 12.16 s
    [Task 15/25]  Current/Best:   11.29/  21.01 GFLOPS | Progress: (20/20
 ) | 14.33 s Done.
+
    [Task 16/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 16/25]  Current/Best:    6.11/  13.27 GFLOPS | Progress: (4/20) | 3.53 s
    [Task 16/25]  Current/Best:   15.81/  19.46 GFLOPS | Progress: (8/20) | 5.01 s
    [Task 16/25]  Current/Best:   15.47/  19.46 GFLOPS | Progress: (12/20) | 6.26 s
    [Task 16/25]  Current/Best:   13.68/  19.46 GFLOPS | Progress: (16/20) | 8.40 s
    [Task 16/25]  Current/Best:   13.06/  19.46 GFLOPS | Progress: (20/20) | 10.74 s Done.
+
    [Task 17/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 17/25]  Current/Best:   14.79/  18.43 GFLOPS | Progress: (4/20) | 3.79 s
    [Task 17/25]  Current/Best:   11.71/  23.35 GFLOPS | Progress: (8/20) | 6.15 s
    [Task 17/25]  Current/Best:   17.75/  23.35 GFLOPS | Progress: (12/20) | 8.42 s
    [Task 17/25]  Current/Best:   14.86/  23.35 GFLOPS | Progress: (16/20) | 10.38 s
    [Task 17/25]  Current/Best:   11.79/  23.35 GFLOPS | Progress: (20/20) | 13.52 s Done.
+
    [Task 18/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 18/25]  Current/Best:   14.30/  20.74 GFLOPS | Progress: (4/20) | 3.66 s
    [Task 18/25]  Current/Best:   14.25/  20.74 GFLOPS | Progress: (8/20) | 9.53 s
    [Task 18/25]  Current/Best:   19.53/  20.74 GFLOPS | Progress: (12/20) | 11.67 s
    [Task 18/25]  Current/Best:   11.70/  20.74 GFLOPS | Progress: (16/20) | 15.04 s
    [Task 18/25]  Current/Best:    9.77/  20.74 GFLOPS | Progress: (20/20) | 20.76 s Done.
+
    [Task 19/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 19/25]  Current/Best:   11.83/  11.83 GFLOPS | Progress: (4/20) | 6.41 s
    [Task 19/25]  Current/Best:    1.55/  11.83 GFLOPS | Progress: (8/20) | 11.82 s
    [Task 19/25]  Current/Best:   10.46/  19.33 GFLOPS | Progress: (12/20) | 15.90 s
    [Task 19/25]  Current/Best:    3.08/  19.33 GFLOPS | Progress: (16/20) | 18.64 s
    [Task 19/25]  Current/Best:   18.05/  19.33 GFLOPS | Progress: (20/20) | 21.15 s Done.
+
    [Task 20/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 20/25]  Current/Best:   16.69/  16.69 GFLOPS | Progress: (4/20) | 3.46 s Done.
+
    [Task 20/25]  Current/Best:   16.05/  16.69 GFLOPS | Progress: (8/20) | 5.99 s
    [Task 20/25]  Current/Best:    7.22/  16.83 GFLOPS | Progress: (12/20) | 8.80 s
    [Task 20/25]  Current/Best:    8.99/  16.83 GFLOPS | Progress: (16/20) | 13.20 s
    [Task 20/25]  Current/Best:    5.98/  16.83 GFLOPS | Progress: (20/20) | 16.45 s
    [Task 21/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 21/25]  Current/Best:    9.36/  16.41 GFLOPS | Progress: (4/20) | 2.99 s
    [Task 21/25]  Current/Best:   19.32/  19.32 GFLOPS | Progress: (8/20) | 6.55 s
    [Task 21/25]  Current/Best:   11.00/  19.32 GFLOPS | Progress: (12/20) | 9.27 s
    [Task 21/25]  Current/Best:    6.93/  19.32 GFLOPS | Progress: (16/20) | 13.89 s
    [Task 21/25]  Current/Best:   16.70/  19.32 GFLOPS | Progress: (20/20) | 16.50 s
    [Task 22/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 22/25]  Current/Best:   19.34/  19.34 GFLOPS | Progress: (4/20)
  | 3.65 s
    [Task 22/25]  Current/Best:   18.26/  19.34 GFLOPS | Progress: (8/20) | 5.16 s
    [Task 22/25]  Current/Best:   11.93/  19.34 GFLOPS | Progress: (12/20) | 6.74 s
    [Task 22/25]  Current/Best:    1.55/  19.34 GFLOPS | Progress: (16/20) | 10.18 s
    [Task 22/25]  Current/Best:    4.99/  19.34 GFLOPS | Progress: (20/20) | 12.11 s Done.
+
    [Task 23/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 23/25]  Current/Best:    9.12/  19.30 GFLOPS | Progress: (4/20) | 4.78 s
    [Task 23/25]  Current/Best:   11.97/  19.30 GFLOPS | Progress: (8/20) | 10.28 s
    [Task 23/25]  Current/Best:    1.55/  19.30 GFLOPS | Progress: (12/20) | 14.99 s
    [Task 23/25]  Current/Best:   11.08/  19.30 GFLOPS | Progress: (16/20) | 18.00 s
    [Task 23/25]  Current/Best:   11.83/  21.38 GFLOPS | Progress: (20/20) | 20.28 s Done.
+
    [Task 24/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 24/25]  Current/Best:    2.73/   2.76 GFLOPS | Progress: (4/20) | 12.15 s
    [Task 24/25]  Current/Best:    4.85/   6.87 GFLOPS | Progress: (8/20) | 24.09 s
    [Task 24/25]  Current/Best:    1.74/   9.97 GFLOPS | Progress: (12/20) | 26.51 s Done.
+
    [Task 24/25]  Current/Best:    6.33/   9.98 GFLOPS | Progress: (16/20) | 37.25 s
    [Task 24/25]  Current/Best:    5.48/   9.98 GFLOPS | Progress: (20/20) | 48.02 s
    [Task 25/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 25/25]  Current/Best:    2.85/   9.35 GFLOPS | Progress: (4/20) | 4.34 s
    [Task 25/25]  Current/Best:    4.89/   9.35 GFLOPS | Progress: (8/20) | 15.04 s
    [Task 25/25]  Current/Best:    5.13/   9.35 GFLOPS | Progress: (12/20) | 17.39 s
    [Task 25/25]  Current/Best:    8.25/   9.35 GFLOPS | Progress: (16/20) | 22.33 s
    [Task 25/25]  Current/Best:    3.00/   9.75 GFLOPS | Progress: (20/20) | 33.08 s
 
 
 
@@ -674,9 +672,9 @@ Verify that the optimized model runs and produces the same results:
 
  .. code-block:: none
 
-    class='n02123045 tabby, tabby cat' with probability=0.621104
-    class='n02123159 tiger cat' with probability=0.356378
-    class='n02124075 Egyptian cat' with probability=0.019713
+    class='n02123045 tabby, tabby cat' with probability=0.621102
+    class='n02123159 tiger cat' with probability=0.356379
+    class='n02124075 Egyptian cat' with probability=0.019712
     class='n02129604 tiger, Panthera tigris' with probability=0.001215
     class='n04040759 radiator' with probability=0.000262
 
@@ -732,8 +730,8 @@ improvement in comparing the optimized model to the unoptimized model.
 
  .. code-block:: none
 
-    optimized: {'mean': 407.06859864999615, 'median': 406.15416939999704, 'std': 4.7846444596952695}
-    unoptimized: {'mean': 520.4171909400009, 'median': 521.4053322000041, 'std': 2.5748459860689517}
+    optimized: {'mean': 401.7012595200026, 'median': 401.2519707500019, 'std': 2.9884877628718733}
+    unoptimized: {'mean': 519.6498904799989, 'median': 519.5562873500023, 'std': 3.6570841684229767}
 
 
 
@@ -756,7 +754,7 @@ profiling/benchmarking.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 11 minutes  5.266 seconds)
+   **Total running time of the script:** ( 11 minutes  22.737 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 50407403ee..a8cd991da4 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -270,7 +270,7 @@ device and returns the measured cost. Network overhead is excluded.
 
  .. code-block:: none
 
-    1.352e-07 secs/op
+    1.252e-07 secs/op
 
 
 
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index f339fb3c98..f9b446f504 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -260,7 +260,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
 
  .. code-block:: none
 
-    [stage(a, placeholder(a, 0x1746e500)), stage(b, placeholder(b, 0x221dfb20)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(mi [...]
+    [stage(a, placeholder(a, 0x17859670)), stage(b, placeholder(b, 0x21a4dbe0)), 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 c122798454..1eca7924b6 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,32 +5,32 @@
 
 Computation times
 =================
-**14:27.429** total execution time for **tutorial** files:
+**14:53.635** total execution time for **tutorial** files:
 
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)                 | 11:05.266 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)                 | 11:22.737 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:25.636 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:29.127 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)     | 01:01.073 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)     | 01:00.338 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)                 | 00:34.649 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)                 | 00:35.055 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)               | 00:18.324 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)               | 00:23.938 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)       | 00:01.452 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)       | 00:01.407 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)                               | 00:00.841 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)                               | 00:00.842 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.178 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.181 | 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``)                                             | 00:00.002 | 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_tvmc_python.py` (``tvmc_python.py``)                             | 00:00.001 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``)   | 00:00.001 | 0.0 MB |
++------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_tutorial_install.py` (``install.py``)                                     | 00:00.001 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index f209d17eb3..19b37de02d 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -294,7 +294,7 @@ helper function to run a profile of the TVM generated code.
 
  .. code-block:: none
 
-    Numpy running time: 0.000007
+    Numpy running time: 0.000008
     naive: 0.000007
 
 
@@ -448,7 +448,7 @@ factor to be the number of threads on your CPU.
 
  .. code-block:: none
 
-    vector: 0.000027
+    vector: 0.000026
     @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, [n: int32], [stride: int32], type="auto"),
@@ -499,10 +499,10 @@ We can now compare the different schedules
  .. code-block:: none
 
                 Operator                  Timing             Performance
-                   numpy    6.9593900002473675e-06                   1.0
-                   naive              6.8121e-06      0.9788357887340512
-                parallel              7.1593e-06      1.0287252186966855
-                  vector    2.6989200000000002e-05      3.87809851136963
+                   numpy    7.938979999835283e-06                    1.0
+                   naive              6.6844e-06      0.8419721425345179
+                parallel    6.976599999999999e-06     0.8787778782847103
+                  vector             2.57611e-05       3.244887882389739
 
 
 
@@ -923,7 +923,7 @@ matrix multiplication.
 
  .. code-block:: none
 
-    Numpy running time: 0.019423
+    Numpy running time: 0.018963
 
 
 
@@ -981,7 +981,7 @@ optimizations.
 
  .. code-block:: none
 
-    none: 3.352588
+    none: 3.302533
 
 
 
@@ -1083,7 +1083,7 @@ schedule.
 
  .. code-block:: none
 
-    blocking: 0.326937
+    blocking: 0.329592
 
 
 
@@ -1178,7 +1178,7 @@ already cache friendly from our previous optimizations.
 
  .. code-block:: none
 
-    vectorization: 0.347545
+    vectorization: 0.349835
     @main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
       attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
       buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1251,7 +1251,7 @@ more cache friendly.
 
  .. code-block:: none
 
-    loop permutation: 0.130719
+    loop permutation: 0.127887
     @main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
       attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
       buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1349,7 +1349,7 @@ optimized schedule.
 
  .. code-block:: none
 
-    array packing: 0.109692
+    array packing: 0.109187
     @main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
       attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
       buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1441,7 +1441,7 @@ to `C` when all the block results are ready.
 
  .. code-block:: none
 
-    block caching: 0.111276
+    block caching: 0.111681
     @main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
       attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
       buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1526,7 +1526,7 @@ of thread-level parallelization.
 
  .. code-block:: none
 
-    parallelization: 0.147532
+    parallelization: 0.146988
     @main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
       attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
       buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1606,13 +1606,13 @@ working, we can compare the results.
  .. code-block:: none
 
                 Operator                  Timing             Performance
-                    none      3.3525881485999998                     1.0
-                blocking            0.3269369669      0.0975177839951874
-           vectorization     0.34754523800000003     0.10366475767240624
-        loop permutation            0.1307187521    0.038990399746711084
-           array packing     0.10969231589999999    0.032718697029877106
-           block caching             0.111276008     0.03319107598899898
-         parallelization            0.1475321574    0.044005452164354766
+                    none            3.3025329219                     1.0
+                blocking            0.3295924132     0.09979988723636408
+           vectorization            0.3498348427     0.10592925217494407
+        loop permutation            0.1278866717     0.03872381433412774
+           array packing     0.10918697709999999     0.03306158626790705
+           block caching            0.1116808201     0.03381671666599109
+         parallelization     0.14698846329999998     0.04450779652347422
 
 
 
@@ -1654,7 +1654,7 @@ the computation for specific platforms.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  1.073 seconds)
+   **Total running time of the script:** ( 1 minutes  0.338 seconds)
 
 
 .. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/commit_hash b/docs/commit_hash
index 47a7757976..148da7b1e6 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-eda84e7804be63a74f0089be221da36c6555b9f9
+f674e12d1a20c817d643e47f35cfc69733326092
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index 37dbe34d2a..b402eb13df 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -579,7 +579,7 @@ 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  15.301 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  13.173 seconds)</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-darknet-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/7716f96385bd5abb6e822041e285be54/from_darknet.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_darknet.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_keras.html b/docs/how_to/compile_models/from_keras.html
index c3e94c481e..be1b94ff72 100644
--- a/docs/how_to/compile_models/from_keras.html
+++ b/docs/how_to/compile_models/from_keras.html
@@ -500,7 +500,7 @@ pip install -U tensorflow --user
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Relay top-1 id: 285, class name: Egyptian cat
 
 1/1 [==============================] - ETA: 0s
-1/1 [==============================] - 1s 998ms/step
+1/1 [==============================] - 1s 1s/step
 Keras top-1 id: 285, class name: Egyptian cat
 </pre></div>
 </div>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index bd896675bf..6799717971 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -434,7 +434,7 @@ to download the full example code</p>
 <span class="nb">print</span><span class="p">(</span><span class="s2">&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.zipbd0bd19d-9e87-4c7d-bad5-36e7261a434b 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.zipffd83e02-4558-44ce-b694-b4db2dfdde8f 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 5a37b8d91e..77503e0428 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -442,13 +442,13 @@ Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdo
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: &quot;https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip&quot; to /workspace/.oneflow/flowvision_cache/resnet18.zip
 
   0%|          | 0.00/41.5M [00:00&lt;?, ?B/s]
- 15%|#5        | 6.33M/41.5M [00:00&lt;00:01, 32.8MB/s]
- 23%|##2       | 9.46M/41.5M [00:00&lt;00:01, 29.6MB/s]
- 39%|###8      | 16.0M/41.5M [00:00&lt;00:00, 34.4MB/s]
- 58%|#####7    | 24.0M/41.5M [00:00&lt;00:00, 40.3MB/s]
- 77%|#######7  | 32.0M/41.5M [00:00&lt;00:00, 49.3MB/s]
- 96%|#########6| 40.0M/41.5M [00:00&lt;00:00, 56.1MB/s]
-100%|##########| 41.5M/41.5M [00:00&lt;00:00, 47.8MB/s]
+ 15%|#5        | 6.33M/41.5M [00:00&lt;00:01, 35.2MB/s]
+ 27%|##6       | 11.1M/41.5M [00:00&lt;00:00, 41.7MB/s]
+ 39%|###8      | 16.0M/41.5M [00:00&lt;00:00, 35.0MB/s]
+ 63%|######3   | 26.2M/41.5M [00:00&lt;00:00, 56.3MB/s]
+ 78%|#######8  | 32.4M/41.5M [00:00&lt;00:00, 56.2MB/s]
+ 92%|#########2| 38.3M/41.5M [00:00&lt;00:00, 57.0MB/s]
+100%|##########| 41.5M/41.5M [00:00&lt;00:00, 49.2MB/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 8932eeea3b..43ae044cd4 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -425,11 +425,10 @@ be unstable.</p>
 Downloading: &quot;https://download.pytorch.org/models/resnet18-f37072fd.pth&quot; to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
 
   0%|          | 0.00/44.7M [00:00&lt;?, ?B/s]
- 18%|#7        | 7.99M/44.7M [00:00&lt;00:00, 66.9MB/s]
- 36%|###5      | 16.0M/44.7M [00:00&lt;00:00, 70.6MB/s]
- 58%|#####8    | 26.0M/44.7M [00:00&lt;00:00, 84.9MB/s]
- 77%|#######6  | 34.3M/44.7M [00:00&lt;00:00, 68.4MB/s]
-100%|##########| 44.7M/44.7M [00:00&lt;00:00, 78.3MB/s]
+ 21%|##        | 9.25M/44.7M [00:00&lt;00:00, 97.0MB/s]
+ 49%|####8     | 21.9M/44.7M [00:00&lt;00:00, 117MB/s]
+ 74%|#######3  | 33.0M/44.7M [00:00&lt;00:00, 80.2MB/s]
+100%|##########| 44.7M/44.7M [00:00&lt;00:00, 102MB/s]
 </pre></div>
 </div>
 </div>
diff --git a/docs/how_to/compile_models/from_tensorflow.html b/docs/how_to/compile_models/from_tensorflow.html
index fda69526e7..1ff5058e4a 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -639,7 +639,7 @@ banana (score = 0.00022)
 desk (score = 0.00019)
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  15.514 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  15.887 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 e276e3aaf2..1ea5bb7244 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -334,7 +334,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>06:00.290</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>06:00.348</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 81%" />
@@ -343,43 +343,43 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:15.514</p></td>
+<td><p>01:15.887</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
-<td><p>01:15.301</p></td>
+<td><p>01:13.173</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="from_paddle.html#sphx-glr-how-to-compile-models-from-paddle-py"><span class="std std-ref">Compile PaddlePaddle Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_paddle.py</span></code>)</p></td>
-<td><p>00:48.878</p></td>
+<td><p>00:49.849</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="from_oneflow.html#sphx-glr-how-to-compile-models-from-oneflow-py"><span class="std std-ref">Compile OneFlow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_oneflow.py</span></code>)</p></td>
-<td><p>00:33.615</p></td>
+<td><p>00:33.582</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
-<td><p>00:29.532</p></td>
+<td><p>00:29.691</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
-<td><p>00:28.036</p></td>
+<td><p>00:27.791</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
-<td><p>00:26.265</p></td>
+<td><p>00:26.084</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>00:23.066</p></td>
+<td><p>00:23.416</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="from_keras.html#sphx-glr-how-to-compile-models-from-keras-py"><span class="std std-ref">Compile Keras Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_keras.py</span></code>)</p></td>
-<td><p>00:17.623</p></td>
+<td><p>00:18.391</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>00:02.461</p></td>
+<td><p>00:02.482</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 </tbody>
diff --git a/docs/how_to/deploy_models/deploy_model_on_adreno.html b/docs/how_to/deploy_models/deploy_model_on_adreno.html
index 7a404394a2..00269360fb 100644
--- a/docs/how_to/deploy_models/deploy_model_on_adreno.html
+++ b/docs/how_to/deploy_models/deploy_model_on_adreno.html
@@ -913,7 +913,7 @@ Top5 predictions:
 Evaluate inference time cost...
 Execution time summary:
  mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)
- 2760.7189    2759.9108    2771.6618    2755.6291      4.8687
+ 2759.0047    2758.5342    2762.9447    2756.1885      2.4528
 </pre></div>
 </div>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-model-on-adreno-py">
diff --git a/docs/how_to/deploy_models/deploy_model_on_android.html b/docs/how_to/deploy_models/deploy_model_on_android.html
index 952d7c249b..159d2f2bf2 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -655,7 +655,7 @@ to the remote android device.</p>
 Evaluate inference time cost...
 Execution time summary:
  mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)
-  16.8982      17.0101      17.3807      16.2455       0.4318
+  16.5858      16.7217      17.1187      15.9205       0.3984
 </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 c2a8ac3b92..980c0efcf2 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -447,33 +447,22 @@ be unstable.</p>
 Downloading: &quot;https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth&quot; to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
 
   0%|          | 0.00/170M [00:00&lt;?, ?B/s]
-  5%|4         | 7.99M/170M [00:00&lt;00:04, 37.7MB/s]
-  9%|8         | 14.9M/170M [00:00&lt;00:03, 51.2MB/s]
- 12%|#2        | 20.4M/170M [00:00&lt;00:03, 50.0MB/s]
- 15%|#5        | 25.5M/170M [00:00&lt;00:03, 45.8MB/s]
- 19%|#8        | 32.0M/170M [00:00&lt;00:03, 37.9MB/s]
- 24%|##3       | 40.1M/170M [00:00&lt;00:02, 48.1MB/s]
- 27%|##6       | 45.3M/170M [00:01&lt;00:02, 45.1MB/s]
- 29%|##9       | 50.0M/170M [00:01&lt;00:02, 44.3MB/s]
- 33%|###2      | 56.0M/170M [00:01&lt;00:02, 47.1MB/s]
- 37%|###6      | 62.3M/170M [00:01&lt;00:02, 49.8MB/s]
- 41%|####1     | 70.4M/170M [00:01&lt;00:01, 58.9MB/s]
- 45%|####5     | 76.6M/170M [00:01&lt;00:01, 60.7MB/s]
- 49%|####8     | 82.6M/170M [00:01&lt;00:01, 56.9MB/s]
- 52%|#####1    | 88.2M/170M [00:01&lt;00:01, 51.2MB/s]
- 57%|#####6    | 96.0M/170M [00:01&lt;00:01, 56.4MB/s]
- 61%|######1   | 104M/170M [00:02&lt;00:01, 59.2MB/s]
- 65%|######4   | 110M/170M [00:02&lt;00:01, 58.8MB/s]
- 68%|######7   | 115M/170M [00:02&lt;00:01, 55.0MB/s]
- 74%|#######3  | 125M/170M [00:02&lt;00:00, 66.6MB/s]
- 77%|#######7  | 131M/170M [00:02&lt;00:00, 62.8MB/s]
- 81%|########1 | 138M/170M [00:02&lt;00:00, 53.1MB/s]
- 85%|########4 | 144M/170M [00:02&lt;00:00, 53.8MB/s]
- 88%|########8 | 150M/170M [00:03&lt;00:00, 53.0MB/s]
- 92%|#########1| 156M/170M [00:03&lt;00:00, 53.9MB/s]
- 95%|#########4| 161M/170M [00:03&lt;00:00, 53.7MB/s]
- 99%|#########8| 168M/170M [00:03&lt;00:00, 54.5MB/s]
-100%|##########| 170M/170M [00:03&lt;00:00, 53.2MB/s]
+  5%|5         | 9.16M/170M [00:00&lt;00:01, 96.0MB/s]
+ 11%|#         | 18.3M/170M [00:00&lt;00:01, 84.7MB/s]
+ 18%|#7        | 29.9M/170M [00:00&lt;00:01, 100MB/s]
+ 24%|##3       | 40.0M/170M [00:00&lt;00:01, 100MB/s]
+ 33%|###2      | 56.0M/170M [00:00&lt;00:01, 105MB/s]
+ 40%|###9      | 67.8M/170M [00:00&lt;00:00, 110MB/s]
+ 46%|####6     | 78.3M/170M [00:00&lt;00:00, 103MB/s]
+ 52%|#####1    | 88.3M/170M [00:00&lt;00:00, 90.6MB/s]
+ 59%|#####9    | 101M/170M [00:01&lt;00:00, 101MB/s]
+ 66%|######5   | 112M/170M [00:01&lt;00:00, 95.2MB/s]
+ 72%|#######1  | 122M/170M [00:01&lt;00:00, 95.3MB/s]
+ 78%|#######7  | 132M/170M [00:01&lt;00:00, 98.9MB/s]
+ 85%|########4 | 144M/170M [00:01&lt;00:00, 99.0MB/s]
+ 91%|#########1| 155M/170M [00:01&lt;00:00, 104MB/s]
+ 99%|#########9| 168M/170M [00:01&lt;00:00, 114MB/s]
+100%|##########| 170M/170M [00:01&lt;00:00, 103MB/s]
 /venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
   for i in range(dim)
 /venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the &#39;trunc&#39; function NOT &#39;floor&#39;). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode=&#39;trunc&#39;), or for actual floor division, use torch.div(a, b, rounding_mode=& [...]
@@ -571,7 +560,7 @@ torchvision rcnn models.</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  28.849 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  25.396 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 9911c56944..f453376734 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -491,8 +491,8 @@ training. Other models require a full post training calibration.</p>
 Downloading: &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]
- 59%|#####8    | 7.99M/13.6M [00:00&lt;00:00, 79.9MB/s]
-100%|##########| 13.6M/13.6M [00:00&lt;00:00, 66.3MB/s]
+ 59%|#####8    | 7.99M/13.6M [00:00&lt;00:00, 49.4MB/s]
+100%|##########| 13.6M/13.6M [00:00&lt;00:00, 54.1MB/s]
 </pre></div>
 </div>
 </div>
@@ -583,7 +583,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
  mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)
-  90.6435      90.5418      92.8492      90.2445       0.3633
+  90.6194      90.4477      99.0254      90.2220       0.8892
 </pre></div>
 </div>
 <div class="admonition note">
@@ -622,7 +622,7 @@ This includes support for the VNNI 8 bit dot product instruction (CascadeLake or
 <div class="section" id="deploy-a-quantized-tflite-model">
 <h2>Deploy a quantized TFLite Model<a class="headerlink" href="#deploy-a-quantized-tflite-model" title="Permalink to this headline">¶</a></h2>
 <p>TODO</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  9.190 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  9.150 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 1fa52d22d3..c02e8e7f77 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -576,7 +576,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
  mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)
-  120.9832     120.6341     128.4909     119.6394      1.4166
+  121.2797     121.2729     122.5077     120.3166      0.4146
 </pre></div>
 </div>
 <div class="admonition note">
@@ -604,7 +604,7 @@ network for ARM CPU</span></a>.</p></li>
 </ul>
 </div></blockquote>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes  29.178 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes  32.735 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 ba4aba39ec..81f4084346 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -514,7 +514,7 @@ for calibration. But the accuracy might be impacted.</p>
   DeprecationWarning,
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  37.785 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  37.360 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 68ac4fecb2..94734350e7 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -456,23 +456,24 @@ 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]
-  5%|5         | 6884/132723 [00:00&lt;00:01, 68831.20KB/s]
- 12%|#1        | 15412/132723 [00:00&lt;00:01, 78503.86KB/s]
- 18%|#7        | 23263/132723 [00:00&lt;00:01, 74839.88KB/s]
- 24%|##3       | 31850/132723 [00:00&lt;00:01, 79061.65KB/s]
- 30%|##9       | 39781/132723 [00:00&lt;00:01, 66048.12KB/s]
- 36%|###6      | 48356/132723 [00:00&lt;00:01, 71890.91KB/s]
- 43%|####2     | 56897/132723 [00:00&lt;00:00, 75912.44KB/s]
- 49%|####8     | 64718/132723 [00:00&lt;00:00, 76268.91KB/s]
- 55%|#####4    | 72504/132723 [00:01&lt;00:00, 62495.16KB/s]
- 61%|######1   | 81028/132723 [00:01&lt;00:00, 68337.98KB/s]
- 67%|######7   | 89481/132723 [00:01&lt;00:00, 72688.89KB/s]
- 74%|#######3  | 98041/132723 [00:01&lt;00:00, 76268.87KB/s]
- 80%|########  | 106595/132723 [00:01&lt;00:00, 78898.36KB/s]
- 87%|########6 | 115179/132723 [00:01&lt;00:00, 80899.82KB/s]
- 93%|#########3| 123764/132723 [00:01&lt;00:00, 82343.45KB/s]
-100%|#########9| 132413/132723 [00:01&lt;00:00, 83559.09KB/s]
-100%|##########| 132723/132723 [00:01&lt;00:00, 75796.48KB/s]
+  5%|4         | 6555/132723 [00:00&lt;00:01, 65536.78KB/s]
+ 11%|#         | 14530/132723 [00:00&lt;00:01, 73890.94KB/s]
+ 17%|#6        | 21920/132723 [00:00&lt;00:01, 55509.89KB/s]
+ 22%|##2       | 29675/132723 [00:00&lt;00:01, 62755.25KB/s]
+ 27%|##7       | 36350/132723 [00:00&lt;00:02, 45201.06KB/s]
+ 33%|###3      | 44368/132723 [00:00&lt;00:01, 53726.66KB/s]
+ 39%|###9      | 52330/132723 [00:00&lt;00:01, 60412.83KB/s]
+ 45%|####5     | 60274/132723 [00:01&lt;00:01, 65538.15KB/s]
+ 51%|#####1    | 68319/132723 [00:01&lt;00:00, 69680.13KB/s]
+ 58%|#####7    | 76355/132723 [00:01&lt;00:00, 72713.74KB/s]
+ 64%|######3   | 84350/132723 [00:01&lt;00:00, 74788.72KB/s]
+ 70%|######9   | 92406/132723 [00:01&lt;00:00, 76470.32KB/s]
+ 76%|#######5  | 100359/132723 [00:01&lt;00:00, 77369.24KB/s]
+ 82%|########1 | 108228/132723 [00:01&lt;00:00, 73505.70KB/s]
+ 87%|########7 | 115708/132723 [00:01&lt;00:00, 62549.62KB/s]
+ 93%|#########2| 123138/132723 [00:01&lt;00:00, 65564.97KB/s]
+ 99%|#########8| 131021/132723 [00:01&lt;00:00, 69122.17KB/s]
+100%|##########| 132723/132723 [00:02&lt;00:00, 66119.05KB/s]
 </pre></div>
 </div>
 <p>Create TVM runtime and do inference
@@ -511,7 +512,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
 <span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
 </pre></div>
 </div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  13.027 seconds)</p>
+<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  12.862 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 486ac01478..3fb0890bea 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -334,7 +334,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>14:23.758</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>14:21.220</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 86%" />
@@ -343,39 +343,39 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>03:28.849</p></td>
+<td><p>03:25.396</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>03:13.027</p></td>
+<td><p>03:12.862</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>02:29.178</p></td>
+<td><p>02:32.735</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>01:37.785</p></td>
+<td><p>01:37.360</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>01:09.190</p></td>
+<td><p>01:09.150</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_adreno.html#sphx-glr-how-to-deploy-models-deploy-model-on-adreno-py"><span class="std std-ref">Deploy the Pretrained Model on Adreno</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_adreno.py</span></code>)</p></td>
-<td><p>00:55.119</p></td>
+<td><p>00:55.016</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:37.633</p></td>
+<td><p>00:36.521</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
-<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_nano.html#sphx-glr-how-to-deploy-models-deploy-model-on-nano-py"><span class="std std-ref">Deploy the Pretrained Model on Jetson Nano</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_nano.py</span></code>)</p></td>
-<td><p>00:26.707</p></td>
+<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>00:26.123</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:26.263</p></td>
+<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>00:26.050</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index f4580b32ae..44c4a97ef5 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -615,7 +615,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
 <span class="n">module</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">params</span></a> <span class="o">=</span> <span class="n">get_mobilenet</span><span class="p">()</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipcc753a8d-e565-4644-ab16-e3e685295079 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.zipf645fbff-4783-4d01-8427-5dd9717de0cc 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 cdb1ccdf34..31bdc3aebf 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -334,7 +334,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:48.957</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:49.273</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 84%" />
@@ -343,15 +343,15 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:45.386</p></td>
+<td><p>00:45.703</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>00:02.490</p></td>
+<td><p>00:02.494</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="use_pass_infra.html#sphx-glr-how-to-extend-tvm-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></td>
-<td><p>00:01.073</p></td>
+<td><p>00:01.069</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 57e7de4377..a79b5a5928 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -519,10 +519,10 @@ profile the execution time of each passes.</p>
 </pre></div>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 7480us [7480us] (46.57%; 46.57%)
-FoldScaleAxis: 8580us [9us] (53.43%; 53.43%)
-        FoldConstant: 8571us [1759us] (53.37%; 99.90%)
-                InferType: 6812us [6812us] (42.42%; 79.47%)
+InferType: 7356us [7356us] (46.88%; 46.88%)
+FoldScaleAxis: 8337us [7us] (53.12%; 53.12%)
+        FoldConstant: 8329us [1675us] (53.08%; 99.91%)
+                InferType: 6654us [6654us] (42.40%; 79.89%)
 </pre></div>
 </div>
 </div>
@@ -544,10 +544,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
 </pre></div>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6849us [6849us] (44.91%; 44.91%)
-FoldScaleAxis: 8401us [6us] (55.09%; 55.09%)
-        FoldConstant: 8394us [1703us] (55.05%; 99.93%)
-                InferType: 6692us [6692us] (43.88%; 79.71%)
+InferType: 6724us [6724us] (44.96%; 44.96%)
+FoldScaleAxis: 8230us [5us] (55.04%; 55.04%)
+        FoldConstant: 8225us [1700us] (55.00%; 99.94%)
+                InferType: 6525us [6525us] (43.64%; 79.34%)
 </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 aeb44f4050..55f500a87f 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -571,7 +571,7 @@ latency of convolution.</p>
 <span class="nb">print</span><span class="p">(</span><span class="s2">&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: 37.816287 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 47.380992 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 8856bbb029..ddb42d0545 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -908,7 +908,7 @@ be able to run on our build server</p>
     <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms&quot;</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 13.363971 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 13.353380 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 9dcc6de652..863fc7345a 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -468,8 +468,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
 <span class="nb">print</span><span class="p">(</span><span class="s2">&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: 0.019378
-Baseline: 3.336809
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019708
+Baseline: 3.144211
 </pre></div>
 </div>
 <p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -528,7 +528,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
 <span class="nb">print</span><span class="p">(</span><span class="s2">&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: 0.325638
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.323363
 </pre></div>
 </div>
 <p>Here is the generated IR after blocking.</p>
@@ -594,7 +594,7 @@ vastly.</p>
 <span class="nb">print</span><span class="p">(</span><span class="s2">&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: 0.353265
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.351613
 </pre></div>
 </div>
 <p>Here is the generated IR after vectorization.</p>
@@ -654,7 +654,7 @@ the access pattern for A matrix is more cache friendly.</p>
 <span class="nb">print</span><span class="p">(</span><span class="s2">&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: 0.121025
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.119467
 </pre></div>
 </div>
 <p>Here is the generated IR after loop permutation.</p>
@@ -736,7 +736,7 @@ flattening.</p>
 <span class="nb">print</span><span class="p">(</span><span class="s2">&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: 0.109749
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109682
 </pre></div>
 </div>
 <p>Here is the generated IR after array packing.</p>
@@ -821,7 +821,7 @@ write to C when all the block results are ready.</p>
 <span class="nb">print</span><span class="p">(</span><span class="s2">&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: 0.111289
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111231
 </pre></div>
 </div>
 <p>Here is the generated IR after blocking.</p>
@@ -910,7 +910,7 @@ write to C when all the block results are ready.</p>
 <span class="nb">print</span><span class="p">(</span><span class="s2">&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: 0.147143
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.147187
 </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 0ab401ff81..37aaf445d6 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -334,7 +334,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:35.433</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:35.075</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 83%" />
@@ -343,15 +343,15 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:32.758</p></td>
+<td><p>00:32.336</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>00:01.573</p></td>
+<td><p>00:01.590</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>00:01.101</p></td>
+<td><p>00:01.148</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 b72ca9d7ac..98c506ac27 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -334,7 +334,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>09:16.064</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>09:10.984</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 85%" />
@@ -343,27 +343,27 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></td>
-<td><p>05:34.391</p></td>
+<td><p>05:41.980</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>01:34.721</p></td>
+<td><p>01:33.775</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="tune_network_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></td>
-<td><p>01:03.847</p></td>
+<td><p>01:02.943</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="tune_sparse_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-sparse-x86-py"><span class="std std-ref">Auto-scheduling Sparse Matrix Multiplication on CPU with Custom Sketch Rule</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_sparse_x86.py</span></code>)</p></td>
-<td><p>00:39.083</p></td>
+<td><p>00:28.478</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></td>
-<td><p>00:12.549</p></td>
+<td><p>00:12.355</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></td>
-<td><p>00:11.474</p></td>
+<td><p>00:11.453</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 6e09d119b8..8de52e232d 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
@@ -497,483 +497,805 @@ cooperative fetching, unrolling and operator fusion.</p>
              bias: Buffer(bias_2: Pointer(float32), float32, [1, 512, 1, 1], []),
              compute: Buffer(compute_2: Pointer(float32), float32, [1, 512, 7, 7], [])}
   buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute} {
-  attr [IterVar(blockIdx.x: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;blockIdx.x&quot;)] &quot;thread_extent&quot; = 28;
-  allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
-  allocate(pad_temp.shared: Pointer(shared float32), float32, [72]), storage_scope = shared;
-  allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
-  attr [IterVar(threadIdx.x: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64 {
-    conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope=&quot;local&quot;, align=32)[0] = 0f32
-    conv2d_nchw_1[1] = 0f32
-    conv2d_nchw_1[2] = 0f32
-    conv2d_nchw_1[3] = 0f32
+  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, [392]), storage_scope = shared;
+  allocate(kernel.shared: Pointer(shared float32), float32, [256]), 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, [16], [], scope=&quot;local&quot;, align=16)[0] = 0f32
     conv2d_nchw_1[4] = 0f32
-    conv2d_nchw_1[5] = 0f32
-    conv2d_nchw_1[6] = 0f32
-    conv2d_nchw_1[7] = 0f32
     conv2d_nchw_1[8] = 0f32
+    conv2d_nchw_1[12] = 0f32
+    conv2d_nchw_1[16] = 0f32
+    conv2d_nchw_1[20] = 0f32
+    conv2d_nchw_1[24] = 0f32
+    conv2d_nchw_1[1] = 0f32
+    conv2d_nchw_1[5] = 0f32
     conv2d_nchw_1[9] = 0f32
+    conv2d_nchw_1[13] = 0f32
+    conv2d_nchw_1[17] = 0f32
+    conv2d_nchw_1[21] = 0f32
+    conv2d_nchw_1[25] = 0f32
+    conv2d_nchw_1[2] = 0f32
+    conv2d_nchw_1[6] = 0f32
     conv2d_nchw_1[10] = 0f32
+    conv2d_nchw_1[14] = 0f32
+    conv2d_nchw_1[18] = 0f32
+    conv2d_nchw_1[22] = 0f32
+    conv2d_nchw_1[26] = 0f32
+    conv2d_nchw_1[3] = 0f32
+    conv2d_nchw_1[7] = 0f32
     conv2d_nchw_1[11] = 0f32
-    conv2d_nchw_1[12] = 0f32
-    conv2d_nchw_1[13] = 0f32
+    conv2d_nchw_1[15] = 0f32
+    conv2d_nchw_1[19] = 0f32
+    conv2d_nchw_1[23] = 0f32
+    conv2d_nchw_1[27] = 0f32
     for (rc.outer.outer: int32, 0, 64) {
       for (ry.outer.outer: int32, 0, 3) {
-        let cse_var_2: int32 = (rc.outer.outer*72)
-        let cse_var_1: int32 = (ry.outer.outer*3)
+        let cse_var_2: int32 = (rc.outer.outer*392)
+        let cse_var_1: int32 = (ry.outer.outer*7)
          {
-          attr [IterVar(threadIdx.x_1: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64 {
-            if @tir.likely((threadIdx.x_1 &lt; 18), dtype=bool) {
-              pad_temp.shared_1: Buffer(pad_temp.shared, float32, [72], [], scope=&quot;shared&quot;)[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 &lt;= (ry.outer.outer + floormod(blockIdx.x, 7))) &amp;&amp; ((ry.outer.outer + floormod(blockIdx.x, 7)) &lt; 8)) &amp;&amp; (1 &lt;= floormod((threadIdx.x_1*4), 9))) &amp;&amp; (floormod((threadIdx.x_1*4), 9) &lt; 8)), data_3: Buffer(data_2, float32, [25088], [])[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*4), 9)*49)) + (ry.outer.out [...]
-            }
-            if @tir.likely((threadIdx.x_1 &lt; 18), dtype=bool) {
-              pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 &lt;= (ry.outer.outer + floormod(blockIdx.x, 7))) &amp;&amp; ((ry.outer.outer + floormod(blockIdx.x, 7)) &lt; 8)) &amp;&amp; (1 &lt;= floormod(((threadIdx.x_1*4) + 1), 9))) &amp;&amp; (floormod(((threadIdx.x_1*4) + 1), 9) &lt; 8)), data_3[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 1), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], [...]
-            }
-            if @tir.likely((threadIdx.x_1 &lt; 18), dtype=bool) {
-              pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 &lt;= (ry.outer.outer + floormod(blockIdx.x, 7))) &amp;&amp; ((ry.outer.outer + floormod(blockIdx.x, 7)) &lt; 8)) &amp;&amp; (1 &lt;= floormod(((threadIdx.x_1*4) + 2), 9))) &amp;&amp; (floormod(((threadIdx.x_1*4) + 2), 9) &lt; 8)), data_3[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 2), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], [...]
-            }
-            if @tir.likely((threadIdx.x_1 &lt; 18), dtype=bool) {
-              pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 &lt;= (ry.outer.outer + floormod(blockIdx.x, 7))) &amp;&amp; ((ry.outer.outer + floormod(blockIdx.x, 7)) &lt; 8)) &amp;&amp; (1 &lt;= floormod(((threadIdx.x_1*4) + 3), 9))) &amp;&amp; (floormod(((threadIdx.x_1*4) + 3), 9) &lt; 8)), data_3[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 3), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], [...]
-            }
+          attr [IterVar(threadIdx.x_1: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
+          pad_temp.shared_1: Buffer(pad_temp.shared, float32, [392], [], scope=&quot;shared&quot;)[threadIdx.x_1] = @tir.if_then_else((((1 &lt;= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) &amp;&amp; ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) &lt; 8)) &amp;&amp; (1 &lt;= floormod(threadIdx.x_1, 7))), data_3: Buffer(data_2, float32, [25088], [])[(((cse_var_2 + cse_var_1) + threadIdx.x_1) - 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((((1 &lt;= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 1), 7))) &amp;&amp; ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 1), 7)) &lt; 8)) &amp;&amp; (1 &lt;= floormod(threadIdx.x_1, 7))), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 56), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 1), 7)*7)) + floormod(threadIdx.x_1, 7)) - 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 + 112)] = @tir.if_then_else((((1 &lt;= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 2), 7))) &amp;&amp; ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 2), 7)) &lt; 8)) &amp;&amp; (1 &lt;= floormod(threadIdx.x_1, 7))), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 112), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 2), 7)*7)) + floormod(threadIdx.x_1, 7)) - 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((((1 &lt;= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 3), 7))) &amp;&amp; ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 3), 7)) &lt; 8)) &amp;&amp; (1 &lt;= floormod(threadIdx.x_1, 7))), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 168), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 7)*7)) + floormod(threadIdx.x_1, 7)) - 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((((1 &lt;= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 4), 7))) &amp;&amp; ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 4), 7)) &lt; 8)) &amp;&amp; (1 &lt;= floormod(threadIdx.x_1, 7))), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 7)*7)) + floormod(threadIdx.x_1, 7)) - 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 + 280)] = @tir.if_then_else((((1 &lt;= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 5), 7))) &amp;&amp; ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 5), 7)) &lt; 8)) &amp;&amp; (1 &lt;= floormod(threadIdx.x_1, 7))), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 280), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 7)*7)) + floormod(threadIdx.x_1, 7)) - 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 + 336)] = @tir.if_then_else((((1 &lt;= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 6), 7))) &amp;&amp; ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 6), 7)) &lt; 8)) &amp;&amp; (1 &lt;= floormod(threadIdx.x_1, 7))), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 336), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 7)*7)) + floormod(threadIdx.x_1, 7)) - 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, [256], [], scope=&quot;shared&quot;)[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3))]
+          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_3[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 32256)]
+          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_3[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 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 + 168)] = kernel_3[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 96768)]
+          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 + 224)] = kernel_3[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 129024)]
           }
-          attr [IterVar(threadIdx.x_2: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope=&quot;shared&quot;)[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 64)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 64), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 128)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 128), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 192)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 256)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 256), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 320)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 320), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 384)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 448)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 448), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 512)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 512), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 576)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 640)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 640), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 704)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 704), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 768)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 147456)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 832)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 832), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 896)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 896), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 960)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 184320)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1024), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1088), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 221184)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1216), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1280), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1408), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1472), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 294912)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1600), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1664), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 331776)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1792), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1856), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 368640)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1984), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2048), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 405504)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2176), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2240), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 442368)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2368), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2432), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 479232)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2560), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2624), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 516096)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2752), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2816), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 552960)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2944), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3008), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*48)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*48)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*48)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*48)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*48)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*48)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*48)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*7)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*32)]))
+          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*32)]))
+          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 2)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*32)]))
+          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 3)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*32)]))
+          conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 4)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*32)]))
+          conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 5)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*32)]))
+          conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 6)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*32)]))
+          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 8)]))
+          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 8)]))
+          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 8)]))
+          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 8)]))
+          conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 8)]))
+          conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 8)]))
+          conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 8)]))
+          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 16)]))
+          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 16)]))
+          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 16)]))
+          conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 16)]))
+          conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 16)]))
+          conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 16)]))
+          conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 16)]))
+          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 24)]))
+          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 24)]))
+          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 24)]))
+          conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 24)]))
+          conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 24)]))
+          conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 24)]))
+          conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 24)]))
+          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 1)]))
+          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 50)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 1)]))
+          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 51)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 1)]))
+          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 52)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 1)]))
+          conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 53)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 1)]))
+          conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 1)]))
+          conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 1)]))
+          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 9)]))
+          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 50)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 9)]))
+          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 51)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 9)]))
+          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 52)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 9)]))
+          conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 53)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 9)]))
+          conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 9)]))
+          conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 9)]))
+          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 17)]))
+          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 50)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 17)]))
+          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 51)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 17)]))
+          conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 52)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 17)]))
+          conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 53)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 17)]))
+          conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 17)]))
+          conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 17)]))
+          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 25)]))
+          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 50)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 25)]))
+          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 51)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 25)]))
+          conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 52)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 25)]))
+          conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 53)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 25)]))
+          conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 25)]))
+          conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 25)]))
+          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 2)]))
+          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 2)]))
+          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 2)]))
+          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 2)]))
+          conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 2)]))
+          conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 2)]))
+          conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 2)]))
+          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 10)]))
+          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 10)]))
+          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 10)]))
+          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 10)]))
+          conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 10)]))
+          conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 10)]))
+          conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 10)]))
+          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 18)]))
+          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 18)]))
+          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 18)]))
+          conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 18)]))
+          conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 18)]))
+          conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 18)]))
+          conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 18)]))
+          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 26)]))
+          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 26)]))
+          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 26)]))
+          conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 26)]))
+          conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 26)]))
+          conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 26)]))
+          conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 26)]))
+          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 3)]))
+          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 3)]))
+          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 3)]))
+          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 150)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 3)]))
+          conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 151)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 3)]))
+          conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 152)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 3)]))
+          conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 3)]))
+          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 11)]))
+          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 11)]))
+          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 11)]))
+          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 150)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 11)]))
+          conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 151)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 11)]))
+          conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 152)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 11)]))
+          conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 11)]))
+          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 19)]))
+          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 19)]))
+          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 19)]))
+          conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 150)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 19)]))
+          conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 151)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 19)]))
+          conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 152)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 19)]))
+          conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 19)]))
+          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 27)]))
+          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 27)]))
+          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 27)]))
+          conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 150)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 27)]))
+          conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 151)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 27)]))
+          conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 152)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 27)]))
+          conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 27)]))
+          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 4)]))
+          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 4)]))
+          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 4)]))
+          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 4)]))
+          conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 4)]))
+          conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 4)]))
+          conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 4)]))
+          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 12)]))
+          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 12)]))
+          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 12)]))
+          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 12)]))
+          conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 12)]))
+          conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 12)]))
+          conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 12)]))
+          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 20)]))
+          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 20)]))
+          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 20)]))
+          conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 20)]))
+          conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 20)]))
+          conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 20)]))
+          conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 20)]))
+          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 28)]))
+          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 28)]))
+          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 28)]))
+          conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 28)]))
+          conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 28)]))
+          conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 28)]))
+          conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 28)]))
+          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 5)]))
+          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 5)]))
+          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 5)]))
+          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 5)]))
+          conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 5)]))
+          conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 5)]))
+          conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 5)]))
+          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 13)]))
+          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 13)]))
+          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 13)]))
+          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 13)]))
+          conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 13)]))
+          conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 13)]))
+          conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 13)]))
+          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 21)]))
+          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 21)]))
+          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 21)]))
+          conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 21)]))
+          conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 21)]))
+          conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 21)]))
+          conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 21)]))
+          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 29)]))
+          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 29)]))
+          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 29)]))
+          conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 29)]))
+          conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 29)]))
+          conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 29)]))
+          conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 29)]))
+          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 6)]))
+          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 295)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 6)]))
+          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 296)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 6)]))
+          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 6)]))
+          conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 6)]))
+          conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 6)]))
+          conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 300)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 6)]))
+          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 14)]))
+          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 295)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 14)]))
+          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 296)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 14)]))
+          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 14)]))
+          conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 14)]))
+          conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 14)]))
+          conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 300)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 14)]))
+          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 22)]))
+          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 295)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 22)]))
+          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 296)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 22)]))
+          conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 22)]))
+          conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 22)]))
+          conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 22)]))
+          conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 300)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 22)]))
+          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 30)]))
+          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 295)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 30)]))
+          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 296)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 30)]))
+          conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 30)]))
+          conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 30)]))
+          conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 30)]))
+          conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 300)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 30)]))
+          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 7)]))
+          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 7)]))
+          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 7)]))
+          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 7)]))
+          conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 7)]))
+          conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 7)]))
+          conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 7)]))
+          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 15)]))
+          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 15)]))
+          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 15)]))
+          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 15)]))
+          conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 15)]))
+          conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 15)]))
+          conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 15)]))
+          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 23)]))
+          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 23)]))
+          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 23)]))
+          conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 23)]))
+          conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 23)]))
+          conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 23)]))
+          conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 23)]))
+          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 31)]))
+          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 31)]))
+          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 31)]))
+          conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 31)]))
+          conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 31)]))
+          conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 31)]))
+          conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 31)]))
+          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] = @tir.if_then_else(((1 &lt;= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) &amp;&amp; ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) &lt; 8)), data_3[(((cse_var_2 + cse_var_1) + threadIdx.x_1) - 7)], 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(((1 &lt;= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 1), 7))) &amp;&amp; ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 1), 7)) &lt; 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 56), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 1), 7)*7)) + floormod(threadIdx.x_1, 7)) - 7)], 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 + 112)] = @tir.if_then_else(((1 &lt;= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 2), 7))) &amp;&amp; ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 2), 7)) &lt; 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 112), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 2), 7)*7)) + floormod(threadIdx.x_1, 7)) - 7)], 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(((1 &lt;= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 3), 7))) &amp;&amp; ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 3), 7)) &lt; 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 168), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 7)*7)) + floormod(threadIdx.x_1, 7)) - 7)], 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(((1 &lt;= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 4), 7))) &amp;&amp; ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 4), 7)) &lt; 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 7)*7)) + floormod(threadIdx.x_1, 7)) - 7)], 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 + 280)] = @tir.if_then_else(((1 &lt;= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 5), 7))) &amp;&amp; ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 5), 7)) &lt; 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 280), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 7)*7)) + floormod(threadIdx.x_1, 7)) - 7)], 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 + 336)] = @tir.if_then_else(((1 &lt;= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 6), 7))) &amp;&amp; ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 6), 7)) &lt; 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 336), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 7)*7)) + floormod(threadIdx.x_1, 7)) - 7)], 0f32, dtype=float32)
+          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
+          kernel.shared_1[threadIdx.x_2] = kernel_3[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 1)]
+          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_3[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 32257)]
+          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_3[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 64513)]
+          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_3[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 96769)]
+          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 + 224)] = kernel_3[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 129025)]
+          }
+          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*7)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*32)]))
+          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*32)]))
+          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 2)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*32)]))
+          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 3)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*32)]))
+          conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 4)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*32)]))
+          conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 5)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*32)]))
+          conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 6)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*32)]))
+          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 8)]))
+          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 8)]))
+          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 8)]))
+          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 8)]))
+          conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 8)]))
+          conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 8)]))
+          conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 8)]))
+          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 16)]))
+          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 16)]))
+          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 16)]))
+          conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 16)]))
+          conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 16)]))
+          conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 16)]))
+          conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 16)]))
+          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 24)]))
+          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 24)]))
+          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 24)]))
+          conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 24)]))
+          conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 24)]))
+          conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 24)]))
+          conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 24)]))
+          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 1)]))
+          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 50)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 1)]))
+          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 51)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 1)]))
+          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 52)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 1)]))
+          conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 53)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 1)]))
+          conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 1)]))
+          conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 1)]))
+          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 9)]))
+          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 50)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 9)]))
+          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 51)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 9)]))
+          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 52)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 9)]))
+          conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 53)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 9)]))
+          conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 9)]))
+          conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 9)]))
+          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 17)]))
+          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 50)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 17)]))
+          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 51)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 17)]))
+          conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 52)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 17)]))
+          conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 53)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 17)]))
+          conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 17)]))
+          conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 17)]))
+          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 25)]))
+          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 50)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 25)]))
+          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 51)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 25)]))
+          conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 52)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 25)]))
+          conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 53)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 25)]))
+          conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 25)]))
+          conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 25)]))
+          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 2)]))
+          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 2)]))
+          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 2)]))
+          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 2)]))
+          conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 2)]))
+          conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 2)]))
+          conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 2)]))
+          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 10)]))
+          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 10)]))
+          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 10)]))
+          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 10)]))
+          conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 10)]))
+          conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 10)]))
+          conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 10)]))
+          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 18)]))
+          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 18)]))
+          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 18)]))
+          conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 18)]))
+          conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 18)]))
+          conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 18)]))
+          conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 18)]))
+          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 26)]))
+          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 26)]))
+          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 26)]))
+          conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 26)]))
+          conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 26)]))
+          conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 26)]))
+          conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 26)]))
+          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 3)]))
+          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 3)]))
+          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 3)]))
+          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 150)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 3)]))
+          conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 151)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 3)]))
+          conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 152)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 3)]))
+          conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 3)]))
+          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 11)]))
+          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 11)]))
+          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 11)]))
+          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 150)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 11)]))
+          conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 151)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 11)]))
+          conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 152)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 11)]))
+          conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 11)]))
+          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 19)]))
+          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 19)]))
+          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 19)]))
+          conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 150)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 19)]))
+          conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 151)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 19)]))
+          conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 152)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 19)]))
+          conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 19)]))
+          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 27)]))
+          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 27)]))
+          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 27)]))
+          conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 150)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 27)]))
+          conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 151)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 27)]))
+          conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 152)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 27)]))
+          conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 27)]))
+          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 4)]))
+          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 4)]))
+          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 4)]))
+          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 4)]))
+          conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 4)]))
+          conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 4)]))
+          conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 4)]))
+          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 12)]))
+          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 12)]))
+          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 12)]))
+          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 12)]))
+          conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 12)]))
+          conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 12)]))
+          conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 12)]))
+          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 20)]))
+          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 20)]))
+          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 20)]))
+          conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 20)]))
+          conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 20)]))
+          conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 20)]))
+          conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 20)]))
+          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 28)]))
+          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 28)]))
+          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 28)]))
+          conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 28)]))
+          conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 28)]))
+          conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 28)]))
+          conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 28)]))
+          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 5)]))
+          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 5)]))
+          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 5)]))
+          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 5)]))
+          conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 5)]))
+          conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 5)]))
+          conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 5)]))
+          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 13)]))
+          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 13)]))
+          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 13)]))
+          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 13)]))
+          conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 13)]))
+          conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 13)]))
+          conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 13)]))
+          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 21)]))
+          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 21)]))
+          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 21)]))
+          conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 21)]))
+          conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 21)]))
+          conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 21)]))
+          conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 21)]))
+          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 29)]))
+          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 29)]))
+          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 29)]))
+          conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 29)]))
+          conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 29)]))
+          conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 29)]))
+          conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 29)]))
+          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 6)]))
+          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 295)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 6)]))
+          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 296)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 6)]))
+          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 6)]))
+          conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 6)]))
+          conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 6)]))
+          conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 300)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 6)]))
+          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 14)]))
+          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 295)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 14)]))
+          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 296)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 14)]))
+          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 14)]))
+          conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 14)]))
+          conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 14)]))
+          conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 300)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 14)]))
+          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 22)]))
+          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 295)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 22)]))
+          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 296)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 22)]))
+          conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 22)]))
+          conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 22)]))
+          conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 22)]))
+          conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 300)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 22)]))
+          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 30)]))
+          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 295)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 30)]))
+          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 296)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 30)]))
+          conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 30)]))
+          conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 30)]))
+          conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 30)]))
+          conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 300)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 30)]))
+          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 7)]))
+          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 7)]))
+          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 7)]))
+          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 7)]))
+          conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 7)]))
+          conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 7)]))
+          conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 7)]))
+          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 15)]))
+          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 15)]))
+          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 15)]))
+          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 15)]))
+          conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 15)]))
+          conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 15)]))
+          conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 15)]))
+          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 23)]))
+          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 23)]))
+          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 23)]))
+          conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 23)]))
+          conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 23)]))
+          conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 23)]))
+          conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 23)]))
+          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 31)]))
+          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 31)]))
+          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 31)]))
+          conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 31)]))
+          conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 31)]))
+          conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 31)]))
+          conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 31)]))
+          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] = @tir.if_then_else((((1 &lt;= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) &amp;&amp; ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) &lt; 8)) &amp;&amp; (floormod(threadIdx.x_1, 7) &lt; 6)), data_3[(((cse_var_2 + cse_var_1) + threadIdx.x_1) - 6)], 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((((1 &lt;= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 1), 7))) &amp;&amp; ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 1), 7)) &lt; 8)) &amp;&amp; (floormod(threadIdx.x_1, 7) &lt; 6)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 56), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 1), 7)*7)) + floormod(threadIdx.x_1, 7)) - 6)], 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 + 112)] = @tir.if_then_else((((1 &lt;= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 2), 7))) &amp;&amp; ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 2), 7)) &lt; 8)) &amp;&amp; (floormod(threadIdx.x_1, 7) &lt; 6)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 112), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 2), 7)*7)) + floormod(threadIdx.x_1, 7)) - 6)], 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((((1 &lt;= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 3), 7))) &amp;&amp; ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 3), 7)) &lt; 8)) &amp;&amp; (floormod(threadIdx.x_1, 7) &lt; 6)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 168), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 7)*7)) + floormod(threadIdx.x_1, 7)) - 6)], 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((((1 &lt;= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 4), 7))) &amp;&amp; ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 4), 7)) &lt; 8)) &amp;&amp; (floormod(threadIdx.x_1, 7) &lt; 6)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 7)*7)) + floormod(threadIdx.x_1, 7)) - 6)], 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 + 280)] = @tir.if_then_else((((1 &lt;= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 5), 7))) &amp;&amp; ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 5), 7)) &lt; 8)) &amp;&amp; (floormod(threadIdx.x_1, 7) &lt; 6)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 280), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 7)*7)) + floormod(threadIdx.x_1, 7)) - 6)], 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 + 336)] = @tir.if_then_else((((1 &lt;= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 6), 7))) &amp;&amp; ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 6), 7)) &lt; 8)) &amp;&amp; (floormod(threadIdx.x_1, 7) &lt; 6)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 336), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 7)*7)) + floormod(threadIdx.x_1, 7)) - 6)], 0f32, dtype=float32)
+          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
+          kernel.shared_1[threadIdx.x_2] = kernel_3[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 2)]
+          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_3[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 32258)]
+          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_3[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 64514)]
+          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_3[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 96770)]
+          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 + 224)] = kernel_3[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 129026)]
+          }
+          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*7)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*32)]))
+          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*32)]))
+          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 2)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*32)]))
+          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 3)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*32)]))
+          conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 4)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*32)]))
+          conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 5)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*32)]))
+          conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 6)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*32)]))
+          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 8)]))
+          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 8)]))
+          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 8)]))
+          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 8)]))
+          conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 8)]))
+          conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 8)]))
+          conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 8)]))
+          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 16)]))
+          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 16)]))
+          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 16)]))
+          conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 16)]))
+          conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 16)]))
+          conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 16)]))
+          conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 16)]))
+          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 24)]))
+          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 24)]))
+          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 24)]))
+          conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 24)]))
+          conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 24)]))
+          conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 24)]))
+          conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 24)]))
+          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 1)]))
+          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 50)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 1)]))
+          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 51)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 1)]))
+          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 52)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 1)]))
+          conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 53)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 1)]))
+          conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 1)]))
+          conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 1)]))
+          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 9)]))
+          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 50)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 9)]))
+          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 51)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 9)]))
+          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 52)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 9)]))
+          conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 53)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 9)]))
+          conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 9)]))
+          conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 9)]))
+          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 17)]))
+          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 50)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 17)]))
+          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 51)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 17)]))
+          conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 52)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 17)]))
+          conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 53)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 17)]))
+          conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 17)]))
+          conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 17)]))
+          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 25)]))
+          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 50)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 25)]))
+          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 51)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 25)]))
+          conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 52)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 25)]))
+          conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 53)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 25)]))
+          conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 25)]))
+          conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 25)]))
+          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 2)]))
+          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 2)]))
+          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 2)]))
+          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 2)]))
+          conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 2)]))
+          conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 2)]))
+          conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 2)]))
+          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 10)]))
+          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 10)]))
+          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 10)]))
+          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 10)]))
+          conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 10)]))
+          conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 10)]))
+          conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 10)]))
+          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 18)]))
+          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 18)]))
+          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 18)]))
+          conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 18)]))
+          conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 18)]))
+          conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 18)]))
+          conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 18)]))
+          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 26)]))
+          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 26)]))
+          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 26)]))
+          conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 26)]))
+          conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 26)]))
+          conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 26)]))
+          conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 26)]))
+          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 3)]))
+          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 3)]))
+          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 3)]))
+          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 150)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 3)]))
+          conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 151)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 3)]))
+          conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 152)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 3)]))
+          conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 3)]))
+          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 11)]))
+          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 11)]))
+          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 11)]))
+          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 150)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 11)]))
+          conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 151)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 11)]))
+          conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 152)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 11)]))
+          conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 11)]))
+          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 19)]))
+          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 19)]))
+          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 19)]))
+          conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 150)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 19)]))
+          conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 151)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 19)]))
+          conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 152)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 19)]))
+          conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 19)]))
+          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 27)]))
+          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 27)]))
+          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 27)]))
+          conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 150)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 27)]))
+          conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 151)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 27)]))
+          conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 152)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 27)]))
+          conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 27)]))
+          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 4)]))
+          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 4)]))
+          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 4)]))
+          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 4)]))
+          conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 4)]))
+          conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 4)]))
+          conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 4)]))
+          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 12)]))
+          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 12)]))
+          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 12)]))
+          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 12)]))
+          conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 12)]))
+          conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 12)]))
+          conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 12)]))
+          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 20)]))
+          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 20)]))
+          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 20)]))
+          conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 20)]))
+          conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 20)]))
+          conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 20)]))
+          conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 20)]))
+          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 28)]))
+          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 28)]))
+          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 28)]))
+          conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 28)]))
+          conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 28)]))
+          conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 28)]))
+          conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 28)]))
+          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 5)]))
+          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 5)]))
+          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 5)]))
+          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 5)]))
+          conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 5)]))
+          conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 5)]))
+          conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 5)]))
+          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 13)]))
+          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 13)]))
+          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 13)]))
+          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 13)]))
+          conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 13)]))
+          conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 13)]))
+          conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 13)]))
+          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 21)]))
+          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 21)]))
+          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 21)]))
+          conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 21)]))
+          conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 21)]))
+          conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 21)]))
+          conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 21)]))
+          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 29)]))
+          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 29)]))
+          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 29)]))
+          conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 29)]))
+          conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 29)]))
+          conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 29)]))
+          conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 29)]))
+          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 6)]))
+          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 295)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 6)]))
+          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 296)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 6)]))
+          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 6)]))
+          conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 6)]))
+          conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 6)]))
+          conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 300)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 6)]))
+          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 14)]))
+          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 295)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 14)]))
+          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 296)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 14)]))
+          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 14)]))
+          conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 14)]))
+          conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 14)]))
+          conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 300)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 14)]))
+          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 22)]))
+          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 295)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 22)]))
+          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 296)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 22)]))
+          conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 22)]))
+          conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 22)]))
+          conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 22)]))
+          conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 300)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 22)]))
+          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 30)]))
+          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 295)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 30)]))
+          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 296)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 30)]))
+          conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 30)]))
+          conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 30)]))
+          conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 30)]))
+          conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 300)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 30)]))
+          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 7)]))
+          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 7)]))
+          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 7)]))
+          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 7)]))
+          conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 7)]))
+          conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 7)]))
+          conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 7)]))
+          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 15)]))
+          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 15)]))
+          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 15)]))
+          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 15)]))
+          conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 15)]))
+          conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 15)]))
+          conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 15)]))
+          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 23)]))
+          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 23)]))
+          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 23)]))
+          conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 23)]))
+          conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 23)]))
+          conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 23)]))
+          conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 23)]))
+          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 31)]))
+          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 31)]))
+          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 31)]))
+          conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 31)]))
+          conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 31)]))
+          conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 31)]))
+          conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*32) + 31)]))
         }
       }
     }
-    for (i1.inner: int32, 0, 2) {
-      for (i3.inner: int32, 0, 7) {
-        compute_3: Buffer(compute_2, float32, [25088], [])[(((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias_3: Buffer(bias_2, float32, [512], [])[(((floordiv(blockIdx.x, 7)*128) + (threadIdx.x*2)) + i1.inner)]), 0f32)
-      }
+    for (i1.inner: int32, 0, 4) {
+      compute_3: Buffer(compute_2, float32, [25088], [])[((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7))] = max((conv2d_nchw_1[i1.inner] + bias_3: Buffer(bias_2, float32, [512], [])[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
+      compute_3[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 1)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias_3[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
+      compute_3[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 2)] = max((conv2d_nchw_1[(i1.inner + 8)] + bias_3[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
+      compute_3[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 3)] = max((conv2d_nchw_1[(i1.inner + 12)] + bias_3[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
+      compute_3[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 4)] = max((conv2d_nchw_1[(i1.inner + 16)] + bias_3[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
+      compute_3[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 5)] = max((conv2d_nchw_1[(i1.inner + 20)] + bias_3[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
+      compute_3[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 6)] = max((conv2d_nchw_1[(i1.inner + 24)] + bias_3[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
     }
   }
 }
@@ -1010,7 +1332,7 @@ 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: 0.356 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.365 ms
 </pre></div>
 </div>
 </div>
@@ -1039,37 +1361,37 @@ 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=1)
-conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
+conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=4)
+conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=8)
 conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
 conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
 conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
-conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
+conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
 conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
 conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
-conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
+conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
 conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
-conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
+conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=7)
+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=8)
 conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
 conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
 conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
-conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
 s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
 compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
 compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
 compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
-compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
+compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=4)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
 compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
 compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
-compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
 compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
-compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
+compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
 compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
-compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
+compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=7)
 s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
 s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
 kernel_shared = s.cache_read(kernel, &quot;shared&quot;, [conv2d_nchw])
@@ -1088,14 +1410,14 @@ s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread
 kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
 kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
 s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
 s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis(&quot;threadIdx.x&quot;))
 pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=4)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
 s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=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;, 512)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, &quot;auto_unroll_max_step&quot;, 1024)
 s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, &quot;unroll_explicit&quot;, True)
 
 CUDA source code:
@@ -1113,430 +1435,770 @@ CUDA source code:
   #define int64_t long long
   #define uint64_t unsigned long long
 #endif
-extern &quot;C&quot; __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
-  float conv2d_nchw[14];
-  __shared__ float pad_temp_shared[72];
-  __shared__ float kernel_shared[3072];
+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[28];
+  __shared__ float pad_temp_shared[392];
+  __shared__ float kernel_shared[256];
   conv2d_nchw[0] = 0.000000e+00f;
-  conv2d_nchw[1] = 0.000000e+00f;
-  conv2d_nchw[2] = 0.000000e+00f;
-  conv2d_nchw[3] = 0.000000e+00f;
   conv2d_nchw[4] = 0.000000e+00f;
-  conv2d_nchw[5] = 0.000000e+00f;
-  conv2d_nchw[6] = 0.000000e+00f;
-  conv2d_nchw[7] = 0.000000e+00f;
   conv2d_nchw[8] = 0.000000e+00f;
+  conv2d_nchw[12] = 0.000000e+00f;
+  conv2d_nchw[16] = 0.000000e+00f;
+  conv2d_nchw[20] = 0.000000e+00f;
+  conv2d_nchw[24] = 0.000000e+00f;
+  conv2d_nchw[1] = 0.000000e+00f;
+  conv2d_nchw[5] = 0.000000e+00f;
   conv2d_nchw[9] = 0.000000e+00f;
+  conv2d_nchw[13] = 0.000000e+00f;
+  conv2d_nchw[17] = 0.000000e+00f;
+  conv2d_nchw[21] = 0.000000e+00f;
+  conv2d_nchw[25] = 0.000000e+00f;
+  conv2d_nchw[2] = 0.000000e+00f;
+  conv2d_nchw[6] = 0.000000e+00f;
   conv2d_nchw[10] = 0.000000e+00f;
+  conv2d_nchw[14] = 0.000000e+00f;
+  conv2d_nchw[18] = 0.000000e+00f;
+  conv2d_nchw[22] = 0.000000e+00f;
+  conv2d_nchw[26] = 0.000000e+00f;
+  conv2d_nchw[3] = 0.000000e+00f;
+  conv2d_nchw[7] = 0.000000e+00f;
   conv2d_nchw[11] = 0.000000e+00f;
-  conv2d_nchw[12] = 0.000000e+00f;
-  conv2d_nchw[13] = 0.000000e+00f;
+  conv2d_nchw[15] = 0.000000e+00f;
+  conv2d_nchw[19] = 0.000000e+00f;
+  conv2d_nchw[23] = 0.000000e+00f;
+  conv2d_nchw[27] = 0.000000e+00f;
   for (int rc_outer_outer = 0; rc_outer_outer &lt; 64; ++rc_outer_outer) {
     for (int ry_outer_outer = 0; ry_outer_outer &lt; 3; ++ry_outer_outer) {
       __syncthreads();
-      if (((int)threadIdx.x) &lt; 18) {
-        pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 &lt;= (ry_outer_outer + (((int)blockIdx.x) % 7))) &amp;&amp; ((ry_outer_outer + (((int)blockIdx.x) % 7)) &lt; 8)) &amp;&amp; (1 &lt;= ((((int)threadIdx.x) * 4) % 9))) &amp;&amp; (((((int)threadIdx.x) * 4) % 9) &lt; 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
-      }
-      if (((int)threadIdx.x) &lt; 18) {
-        pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 &lt;= (ry_outer_outer + (((int)blockIdx.x) % 7))) &amp;&amp; ((ry_outer_outer + (((int)blockIdx.x) % 7)) &lt; 8)) &amp;&amp; (1 &lt;= (((((int)threadIdx.x) * 4) + 1) % 9))) &amp;&amp; ((((((int)threadIdx.x) * 4) + 1) % 9) &lt; 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
+      pad_temp_shared[((int)threadIdx.x)] = ((((1 &lt;= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) &amp;&amp; ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) &lt; 8)) &amp;&amp; (1 &lt;= (((int)threadIdx.x) % 7))) ? data[((((rc_outer_outer * 392) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) - 8)] : 0.000000e+00f);
+      pad_temp_shared[(((int)threadIdx.x) + 56)] = ((((1 &lt;= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 1) % 7))) &amp;&amp; ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 1) % 7)) &lt; 8)) &amp;&amp; (1 &lt;= (((int)threadIdx.x) % 7))) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 56) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 1) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+      pad_temp_shared[(((int)threadIdx.x) + 112)] = ((((1 &lt;= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 2) % 7))) &amp;&amp; ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 2) % 7)) &lt; 8)) &amp;&amp; (1 &lt;= (((int)threadIdx.x) % 7))) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 112) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 2) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+      pad_temp_shared[(((int)threadIdx.x) + 168)] = ((((1 &lt;= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 3) % 7))) &amp;&amp; ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 3) % 7)) &lt; 8)) &amp;&amp; (1 &lt;= (((int)threadIdx.x) % 7))) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 168) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 3) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+      pad_temp_shared[(((int)threadIdx.x) + 224)] = ((((1 &lt;= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 4) % 7))) &amp;&amp; ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 4) % 7)) &lt; 8)) &amp;&amp; (1 &lt;= (((int)threadIdx.x) % 7))) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 4) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+      pad_temp_shared[(((int)threadIdx.x) + 280)] = ((((1 &lt;= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 5) % 7))) &amp;&amp; ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 5) % 7)) &lt; 8)) &amp;&amp; (1 &lt;= (((int)threadIdx.x) % 7))) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 280) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 5) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+      pad_temp_shared[(((int)threadIdx.x) + 336)] = ((((1 &lt;= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 6) % 7))) &amp;&amp; ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 6) % 7)) &lt; 8)) &amp;&amp; (1 &lt;= (((int)threadIdx.x) % 7))) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 336) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 6) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+      kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) &gt;&gt; 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) &amp; 7) * 9)) + (ry_outer_outer * 3))];
+      kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) &gt;&gt; 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) &amp; 7) * 9)) + (ry_outer_outer * 3)) + 32256)];
+      kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) &gt;&gt; 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) &amp; 7) * 9)) + (ry_outer_outer * 3)) + 64512)];
+      kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) &gt;&gt; 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) &amp; 7) * 9)) + (ry_outer_outer * 3)) + 96768)];
+      if (((int)threadIdx.x) &lt; 32) {
+        kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) &gt;&gt; 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) &amp; 7) * 9)) + (ry_outer_outer * 3)) + 129024)];
       }
-      if (((int)threadIdx.x) &lt; 18) {
-        pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 &lt;= (ry_outer_outer + (((int)blockIdx.x) % 7))) &amp;&amp; ((ry_outer_outer + (((int)blockIdx.x) % 7)) &lt; 8)) &amp;&amp; (1 &lt;= (((((int)threadIdx.x) * 4) + 2) % 9))) &amp;&amp; ((((((int)threadIdx.x) * 4) + 2) % 9) &lt; 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
+      __syncthreads();
+      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 7)] * kernel_shared[((((int)threadIdx.x) / 7) * 32)]));
+      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1)] * kernel_shared[((((int)threadIdx.x) / 7) * 32)]));
+      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 2)] * kernel_shared[((((int)threadIdx.x) / 7) * 32)]));
+      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 3)] * kernel_shared[((((int)threadIdx.x) / 7) * 32)]));
+      conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 4)] * kernel_shared[((((int)threadIdx.x) / 7) * 32)]));
+      conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 5)] * kernel_shared[((((int)threadIdx.x) / 7) * 32)]));
+      conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 6)] * kernel_shared[((((int)threadIdx.x) / 7) * 32)]));
+      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 8)]));
+      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 8)]));
+      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 8)]));
+      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 8)]));
+      conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 8)]));
+      conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 8)]));
+      conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 8)]));
+      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 16)]));
+      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 16)]));
+      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 16)]));
+      conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 16)]));
+      conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 16)]));
+      conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 16)]));
+      conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 16)]));
+      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 24)]));
+      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 24)]));
+      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 24)]));
+      conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 24)]));
+      conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 24)]));
+      conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 24)]));
+      conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 24)]));
+      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 49)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 1)]));
+      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 50)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 1)]));
+      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 51)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 1)]));
+      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 52)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 1)]));
+      conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 53)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 1)]));
+      conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 1)]));
+      conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 1)]));
+      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 49)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 9)]));
+      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 50)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 9)]));
+      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 51)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 9)]));
+      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 52)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 9)]));
+      conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 53)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 9)]));
+      conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 9)]));
+      conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 9)]));
+      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 49)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 17)]));
+      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 50)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 17)]));
+      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 51)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 17)]));
+      conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 52)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 17)]));
+      conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 53)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 17)]));
+      conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 17)]));
+      conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 17)]));
+      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 49)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 25)]));
+      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 50)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 25)]));
+      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 51)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 25)]));
+      conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 52)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 25)]));
+      conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 53)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 25)]));
+      conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 25)]));
+      conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 25)]));
+      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 2)]));
+      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 2)]));
+      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 2)]));
+      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 2)]));
+      conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 2)]));
+      conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 2)]));
+      conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 2)]));
+      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 10)]));
+      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 10)]));
+      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 10)]));
+      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 10)]));
+      conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 10)]));
+      conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 10)]));
+      conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 10)]));
+      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 18)]));
+      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 18)]));
+      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 18)]));
+      conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 18)]));
+      conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 18)]));
+      conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 18)]));
+      conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 18)]));
+      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 26)]));
+      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 26)]));
+      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 26)]));
+      conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 26)]));
+      conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 26)]));
+      conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 26)]));
+      conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 26)]));
+      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 3)]));
+      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 3)]));
+      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 3)]));
+      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 150)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 3)]));
+      conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 151)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 3)]));
+      conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 152)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 3)]));
+      conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 3)]));
+      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 11)]));
+      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 11)]));
+      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 11)]));
+      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 150)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 11)]));
+      conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 151)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 11)]));
+      conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 152)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 11)]));
+      conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 11)]));
+      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 19)]));
+      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 19)]));
+      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 19)]));
+      conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 150)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 19)]));
+      conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 151)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 19)]));
+      conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 152)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 19)]));
+      conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 19)]));
+      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 27)]));
+      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 27)]));
+      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 27)]));
+      conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 150)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 27)]));
+      conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 151)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 27)]));
+      conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 152)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 27)]));
+      conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 27)]));
+      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 4)]));
+      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 4)]));
+      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 4)]));
+      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 4)]));
+      conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 4)]));
+      conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 4)]));
+      conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 4)]));
+      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 12)]));
+      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 12)]));
+      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 12)]));
+      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 12)]));
+      conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 12)]));
+      conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 12)]));
+      conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 12)]));
+      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 20)]));
+      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 20)]));
+      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 20)]));
+      conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 20)]));
+      conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 20)]));
+      conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 20)]));
+      conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 20)]));
+      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 28)]));
+      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 28)]));
+      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 28)]));
+      conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 28)]));
+      conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 28)]));
+      conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 28)]));
+      conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 28)]));
+      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 5)]));
+      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 5)]));
+      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 5)]));
+      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 5)]));
+      conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 5)]));
+      conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 5)]));
+      conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 5)]));
+      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 13)]));
+      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 13)]));
+      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 13)]));
+      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 13)]));
+      conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 13)]));
+      conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 13)]));
+      conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 13)]));
+      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 21)]));
+      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 21)]));
+      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 21)]));
+      conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 21)]));
+      conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 21)]));
+      conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 21)]));
+      conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 21)]));
+      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 29)]));
+      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 29)]));
+      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 29)]));
+      conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 29)]));
+      conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 29)]));
+      conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 29)]));
+      conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 29)]));
+      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 294)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 6)]));
+      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 295)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 6)]));
+      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 296)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 6)]));
+      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 6)]));
+      conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 6)]));
+      conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 6)]));
+      conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 300)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 6)]));
+      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 294)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 14)]));
+      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 295)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 14)]));
+      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 296)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 14)]));
+      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 14)]));
+      conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 14)]));
+      conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 14)]));
+      conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 300)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 14)]));
+      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 294)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 22)]));
+      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 295)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 22)]));
+      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 296)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 22)]));
+      conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 22)]));
+      conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 22)]));
+      conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 22)]));
+      conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 300)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 22)]));
+      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 294)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 30)]));
+      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 295)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 30)]));
+      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 296)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 30)]));
+      conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 30)]));
+      conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 30)]));
+      conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 30)]));
+      conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 300)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 30)]));
+      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 7)]));
+      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 7)]));
+      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 7)]));
+      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 7)]));
+      conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 7)]));
+      conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 7)]));
+      conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 7)]));
+      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 15)]));
+      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 15)]));
+      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 15)]));
+      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 15)]));
+      conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 15)]));
+      conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 15)]));
+      conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 15)]));
+      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 23)]));
+      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 23)]));
+      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 23)]));
+      conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 23)]));
+      conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 23)]));
+      conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 23)]));
+      conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 23)]));
+      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 31)]));
+      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 31)]));
+      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 31)]));
+      conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 31)]));
+      conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 31)]));
+      conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 31)]));
+      conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 31)]));
+      __syncthreads();
+      pad_temp_shared[((int)threadIdx.x)] = (((1 &lt;= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) &amp;&amp; ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) &lt; 8)) ? data[((((rc_outer_outer * 392) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) - 7)] : 0.000000e+00f);
+      pad_temp_shared[(((int)threadIdx.x) + 56)] = (((1 &lt;= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 1) % 7))) &amp;&amp; ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 1) % 7)) &lt; 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 56) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 1) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 7)] : 0.000000e+00f);
+      pad_temp_shared[(((int)threadIdx.x) + 112)] = (((1 &lt;= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 2) % 7))) &amp;&amp; ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 2) % 7)) &lt; 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 112) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 2) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 7)] : 0.000000e+00f);
+      pad_temp_shared[(((int)threadIdx.x) + 168)] = (((1 &lt;= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 3) % 7))) &amp;&amp; ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 3) % 7)) &lt; 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 168) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 3) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 7)] : 0.000000e+00f);
+      pad_temp_shared[(((int)threadIdx.x) + 224)] = (((1 &lt;= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 4) % 7))) &amp;&amp; ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 4) % 7)) &lt; 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 4) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 7)] : 0.000000e+00f);
+      pad_temp_shared[(((int)threadIdx.x) + 280)] = (((1 &lt;= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 5) % 7))) &amp;&amp; ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 5) % 7)) &lt; 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 280) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 5) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 7)] : 0.000000e+00f);
+      pad_temp_shared[(((int)threadIdx.x) + 336)] = (((1 &lt;= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 6) % 7))) &amp;&amp; ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 6) % 7)) &lt; 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 336) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 6) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 7)] : 0.000000e+00f);
+      kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) &gt;&gt; 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) &amp; 7) * 9)) + (ry_outer_outer * 3)) + 1)];
+      kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) &gt;&gt; 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) &amp; 7) * 9)) + (ry_outer_outer * 3)) + 32257)];
+      kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) &gt;&gt; 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) &amp; 7) * 9)) + (ry_outer_outer * 3)) + 64513)];
+      kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) &gt;&gt; 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) &amp; 7) * 9)) + (ry_outer_outer * 3)) + 96769)];
+      if (((int)threadIdx.x) &lt; 32) {
+        kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) &gt;&gt; 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) &amp; 7) * 9)) + (ry_outer_outer * 3)) + 129025)];
       }
-      if (((int)threadIdx.x) &lt; 18) {
-        pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 &lt;= (ry_outer_outer + (((int)blockIdx.x) % 7))) &amp;&amp; ((ry_outer_outer + (((int)blockIdx.x) % 7)) &lt; 8)) &amp;&amp; (1 &lt;= (((((int)threadIdx.x) * 4) + 3) % 9))) &amp;&amp; ((((((int)threadIdx.x) * 4) + 3) % 9) &lt; 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
+      __syncthreads();
+      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 7)] * kernel_shared[((((int)threadIdx.x) / 7) * 32)]));
+      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1)] * kernel_shared[((((int)threadIdx.x) / 7) * 32)]));
+      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 2)] * kernel_shared[((((int)threadIdx.x) / 7) * 32)]));
+      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 3)] * kernel_shared[((((int)threadIdx.x) / 7) * 32)]));
+      conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 4)] * kernel_shared[((((int)threadIdx.x) / 7) * 32)]));
+      conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 5)] * kernel_shared[((((int)threadIdx.x) / 7) * 32)]));
+      conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 6)] * kernel_shared[((((int)threadIdx.x) / 7) * 32)]));
+      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 8)]));
+      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 8)]));
+      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 8)]));
+      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 8)]));
+      conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 8)]));
+      conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 8)]));
+      conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 8)]));
+      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 16)]));
+      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 16)]));
+      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 16)]));
+      conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 16)]));
+      conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 16)]));
+      conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 16)]));
+      conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 16)]));
+      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 24)]));
+      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 24)]));
+      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 24)]));
+      conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 24)]));
+      conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 24)]));
+      conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 24)]));
+      conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 24)]));
+      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 49)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 1)]));
+      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 50)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 1)]));
+      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 51)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 1)]));
+      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 52)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 1)]));
+      conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 53)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 1)]));
+      conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 1)]));
+      conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 1)]));
+      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 49)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 9)]));
+      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 50)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 9)]));
+      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 51)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 9)]));
+      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 52)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 9)]));
+      conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 53)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 9)]));
+      conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 9)]));
+      conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 9)]));
+      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 49)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 17)]));
+      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 50)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 17)]));
+      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 51)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 17)]));
+      conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 52)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 17)]));
+      conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 53)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 17)]));
+      conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 17)]));
+      conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 17)]));
+      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 49)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 25)]));
+      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 50)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 25)]));
+      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 51)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 25)]));
+      conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 52)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 25)]));
+      conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 53)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 25)]));
+      conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 25)]));
+      conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 25)]));
+      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 2)]));
+      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 2)]));
+      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 2)]));
+      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 2)]));
+      conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 2)]));
+      conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 2)]));
+      conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 2)]));
+      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 10)]));
+      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 10)]));
+      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 10)]));
+      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 10)]));
+      conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 10)]));
+      conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 10)]));
+      conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 10)]));
+      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 18)]));
+      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 18)]));
+      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 18)]));
+      conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 18)]));
+      conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 18)]));
+      conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 18)]));
+      conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 18)]));
+      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 26)]));
+      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 26)]));
+      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 26)]));
+      conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 26)]));
+      conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 26)]));
+      conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 26)]));
+      conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 26)]));
+      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 3)]));
+      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 3)]));
+      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 3)]));
+      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 150)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 3)]));
+      conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 151)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 3)]));
+      conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 152)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 3)]));
+      conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 3)]));
+      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 11)]));
+      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 11)]));
+      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 11)]));
+      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 150)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 11)]));
+      conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 151)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 11)]));
+      conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 152)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 11)]));
+      conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 11)]));
+      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 19)]));
+      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 19)]));
+      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 19)]));
+      conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 150)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 19)]));
+      conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 151)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 19)]));
+      conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 152)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 19)]));
+      conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 19)]));
+      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 27)]));
+      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 27)]));
+      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 27)]));
+      conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 150)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 27)]));
+      conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 151)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 27)]));
+      conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 152)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 27)]));
+      conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 27)]));
+      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 4)]));
+      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 4)]));
+      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 4)]));
+      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 4)]));
+      conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 4)]));
+      conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 4)]));
+      conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 4)]));
+      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 12)]));
+      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 12)]));
+      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 12)]));
+      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 12)]));
+      conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 12)]));
+      conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 12)]));
+      conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 12)]));
+      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 20)]));
+      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 20)]));
+      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 20)]));
+      conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 20)]));
+      conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 20)]));
+      conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 20)]));
+      conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 20)]));
+      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 28)]));
+      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 28)]));
+      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 28)]));
+      conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 28)]));
+      conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 28)]));
+      conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 28)]));
+      conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 28)]));
+      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 5)]));
+      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 5)]));
+      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 5)]));
+      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 5)]));
+      conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 5)]));
+      conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 5)]));
+      conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 5)]));
+      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 13)]));
+      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 13)]));
+      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 13)]));
+      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 13)]));
+      conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 13)]));
+      conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 13)]));
+      conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 13)]));
+      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 21)]));
+      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 21)]));
+      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 21)]));
+      conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 21)]));
+      conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 21)]));
+      conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 21)]));
+      conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 21)]));
+      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 29)]));
+      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 29)]));
+      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 29)]));
+      conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 29)]));
+      conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 29)]));
+      conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 29)]));
+      conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 29)]));
+      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 294)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 6)]));
+      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 295)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 6)]));
+      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 296)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 6)]));
+      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 6)]));
+      conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 6)]));
+      conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 6)]));
+      conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 300)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 6)]));
+      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 294)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 14)]));
+      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 295)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 14)]));
+      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 296)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 14)]));
+      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 14)]));
+      conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 14)]));
+      conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 14)]));
+      conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 300)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 14)]));
+      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 294)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 22)]));
+      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 295)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 22)]));
+      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 296)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 22)]));
+      conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 22)]));
+      conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 22)]));
+      conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 22)]));
+      conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 300)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 22)]));
+      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 294)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 30)]));
+      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 295)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 30)]));
+      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 296)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 30)]));
+      conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 30)]));
+      conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 30)]));
+      conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 30)]));
+      conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 300)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 30)]));
+      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 7)]));
+      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 7)]));
+      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 7)]));
+      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 7)]));
+      conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 7)]));
+      conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 7)]));
+      conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 7)]));
+      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 15)]));
+      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 15)]));
+      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 15)]));
+      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 15)]));
+      conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 15)]));
+      conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 15)]));
+      conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 15)]));
+      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 23)]));
+      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 23)]));
+      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 23)]));
+      conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 23)]));
+      conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 23)]));
+      conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 23)]));
+      conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 23)]));
+      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 31)]));
+      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 31)]));
+      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 31)]));
+      conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 31)]));
+      conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 31)]));
+      conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 31)]));
+      conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 31)]));
+      __syncthreads();
+      pad_temp_shared[((int)threadIdx.x)] = ((((1 &lt;= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) &amp;&amp; ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) &lt; 8)) &amp;&amp; ((((int)threadIdx.x) % 7) &lt; 6)) ? data[((((rc_outer_outer * 392) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) - 6)] : 0.000000e+00f);
+      pad_temp_shared[(((int)threadIdx.x) + 56)] = ((((1 &lt;= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 1) % 7))) &amp;&amp; ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 1) % 7)) &lt; 8)) &amp;&amp; ((((int)threadIdx.x) % 7) &lt; 6)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 56) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 1) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 6)] : 0.000000e+00f);
+      pad_temp_shared[(((int)threadIdx.x) + 112)] = ((((1 &lt;= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 2) % 7))) &amp;&amp; ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 2) % 7)) &lt; 8)) &amp;&amp; ((((int)threadIdx.x) % 7) &lt; 6)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 112) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 2) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 6)] : 0.000000e+00f);
+      pad_temp_shared[(((int)threadIdx.x) + 168)] = ((((1 &lt;= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 3) % 7))) &amp;&amp; ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 3) % 7)) &lt; 8)) &amp;&amp; ((((int)threadIdx.x) % 7) &lt; 6)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 168) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 3) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 6)] : 0.000000e+00f);
+      pad_temp_shared[(((int)threadIdx.x) + 224)] = ((((1 &lt;= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 4) % 7))) &amp;&amp; ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 4) % 7)) &lt; 8)) &amp;&amp; ((((int)threadIdx.x) % 7) &lt; 6)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 4) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 6)] : 0.000000e+00f);
+      pad_temp_shared[(((int)threadIdx.x) + 280)] = ((((1 &lt;= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 5) % 7))) &amp;&amp; ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 5) % 7)) &lt; 8)) &amp;&amp; ((((int)threadIdx.x) % 7) &lt; 6)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 280) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 5) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 6)] : 0.000000e+00f);
+      pad_temp_shared[(((int)threadIdx.x) + 336)] = ((((1 &lt;= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 6) % 7))) &amp;&amp; ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 6) % 7)) &lt; 8)) &amp;&amp; ((((int)threadIdx.x) % 7) &lt; 6)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 336) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 6) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 6)] : 0.000000e+00f);
+      kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) &gt;&gt; 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) &amp; 7) * 9)) + (ry_outer_outer * 3)) + 2)];
+      kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) &gt;&gt; 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) &amp; 7) * 9)) + (ry_outer_outer * 3)) + 32258)];
+      kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) &gt;&gt; 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) &amp; 7) * 9)) + (ry_outer_outer * 3)) + 64514)];
+      kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) &gt;&gt; 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) &amp; 7) * 9)) + (ry_outer_outer * 3)) + 96770)];
+      if (((int)threadIdx.x) &lt; 32) {
+        kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) &gt;&gt; 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) &amp; 7) * 9)) + (ry_outer_outer * 3)) + 129026)];
       }
-      kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
-      kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
-      kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
-      kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
-      kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
-      kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
-      kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
-      kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
-      kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
-      kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
-      kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
-      kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
-      kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
-      kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
-      kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
-      kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
       __syncthreads();
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 48)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 48)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 48)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 48)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 48)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 48)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 48)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 7)] * kernel_shared[((((int)threadIdx.x) / 7) * 32)]));
+      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1)] * kernel_shared[((((int)threadIdx.x) / 7) * 32)]));
+      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 2)] * kernel_shared[((((int)threadIdx.x) / 7) * 32)]));
+      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 3)] * kernel_shared[((((int)threadIdx.x) / 7) * 32)]));
+      conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 4)] * kernel_shared[((((int)threadIdx.x) / 7) * 32)]));
+      conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 5)] * kernel_shared[((((int)threadIdx.x) / 7) * 32)]));
+      conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 6)] * kernel_shared[((((int)threadIdx.x) / 7) * 32)]));
+      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 8)]));
+      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 8)]));
+      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 8)]));
+      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 8)]));
+      conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 8)]));
+      conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 8)]));
+      conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 8)]));
+      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 16)]));
+      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 16)]));
+      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 16)]));
+      conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 16)]));
+      conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 16)]));
+      conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 16)]));
+      conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 16)]));
+      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 24)]));
+      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 24)]));
+      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 24)]));
+      conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 24)]));
+      conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 24)]));
+      conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 24)]));
+      conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 24)]));
+      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 49)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 1)]));
+      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 50)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 1)]));
+      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 51)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 1)]));
+      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 52)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 1)]));
+      conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 53)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 1)]));
+      conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 1)]));
+      conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 1)]));
+      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 49)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 9)]));
+      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 50)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 9)]));
+      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 51)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 9)]));
+      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 52)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 9)]));
+      conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 53)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 9)]));
+      conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 9)]));
+      conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 9)]));
+      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 49)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 17)]));
+      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 50)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 17)]));
+      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 51)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 17)]));
+      conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 52)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 17)]));
+      conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 53)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 17)]));
+      conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 17)]));
+      conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 17)]));
+      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 49)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 25)]));
+      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 50)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 25)]));
+      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 51)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 25)]));
+      conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 52)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 25)]));
+      conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 53)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 25)]));
+      conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 25)]));
+      conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 25)]));
+      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 2)]));
+      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 2)]));
+      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 2)]));
+      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 2)]));
+      conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 2)]));
+      conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 2)]));
+      conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 2)]));
+      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 10)]));
+      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 10)]));
+      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 10)]));
+      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 10)]));
+      conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 10)]));
+      conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 10)]));
+      conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 10)]));
+      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 18)]));
+      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 18)]));
+      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 18)]));
+      conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 18)]));
+      conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 18)]));
+      conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 18)]));
+      conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 18)]));
+      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 26)]));
+      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 26)]));
+      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 26)]));
+      conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 26)]));
+      conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 26)]));
+      conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 26)]));
+      conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 26)]));
+      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 3)]));
+      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 3)]));
+      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 3)]));
+      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 150)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 3)]));
+      conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 151)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 3)]));
+      conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 152)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 3)]));
+      conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 3)]));
+      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 11)]));
+      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 11)]));
+      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 11)]));
+      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 150)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 11)]));
+      conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 151)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 11)]));
+      conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 152)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 11)]));
+      conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 11)]));
+      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 19)]));
+      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 19)]));
+      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 19)]));
+      conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 150)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 19)]));
+      conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 151)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 19)]));
+      conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 152)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 19)]));
+      conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 19)]));
+      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 27)]));
+      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 27)]));
+      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 27)]));
+      conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 150)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 27)]));
+      conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 151)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 27)]));
+      conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 152)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 27)]));
+      conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 27)]));
+      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 4)]));
+      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 4)]));
+      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 4)]));
+      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 4)]));
+      conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 4)]));
+      conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 4)]));
+      conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 4)]));
+      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 12)]));
+      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 12)]));
+      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 12)]));
+      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 12)]));
+      conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 12)]));
+      conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 12)]));
+      conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 12)]));
+      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 20)]));
+      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 20)]));
+      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 20)]));
+      conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 20)]));
+      conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 20)]));
+      conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 20)]));
+      conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 20)]));
+      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 28)]));
+      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 28)]));
+      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 28)]));
+      conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 28)]));
+      conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 28)]));
+      conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 28)]));
+      conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 28)]));
+      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 5)]));
+      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 5)]));
+      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 5)]));
+      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 5)]));
+      conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 5)]));
+      conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 5)]));
+      conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 5)]));
+      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 13)]));
+      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 13)]));
+      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 13)]));
+      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 13)]));
+      conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 13)]));
+      conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 13)]));
+      conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 13)]));
+      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 21)]));
+      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 21)]));
+      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 21)]));
+      conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 21)]));
+      conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 21)]));
+      conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 21)]));
+      conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 21)]));
+      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 29)]));
+      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 29)]));
+      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 29)]));
+      conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 29)]));
+      conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 29)]));
+      conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 29)]));
+      conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 29)]));
+      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 294)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 6)]));
+      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 295)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 6)]));
+      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 296)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 6)]));
+      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 6)]));
+      conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 6)]));
+      conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 6)]));
+      conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 300)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 6)]));
+      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 294)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 14)]));
+      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 295)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 14)]));
+      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 296)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 14)]));
+      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 14)]));
+      conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 14)]));
+      conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 14)]));
+      conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 300)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 14)]));
+      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 294)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 22)]));
+      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 295)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 22)]));
+      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 296)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 22)]));
+      conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 22)]));
+      conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 22)]));
+      conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 22)]));
+      conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 300)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 22)]));
+      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 294)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 30)]));
+      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 295)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 30)]));
+      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 296)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 30)]));
+      conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 30)]));
+      conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 30)]));
+      conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 30)]));
+      conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 300)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 30)]));
+      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 7)]));
+      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 7)]));
+      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 7)]));
+      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 7)]));
+      conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 7)]));
+      conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 7)]));
+      conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 7)]));
+      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 15)]));
+      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 15)]));
+      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 15)]));
+      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 15)]));
+      conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 15)]));
+      conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 15)]));
+      conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 15)]));
+      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 23)]));
+      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 23)]));
+      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 23)]));
+      conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 23)]));
+      conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 23)]));
+      conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 23)]));
+      conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 23)]));
+      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 31)]));
+      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 31)]));
+      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 31)]));
+      conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 31)]));
+      conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 31)]));
+      conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 31)]));
+      conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 32) + 31)]));
     }
   }
-  for (int i1_inner = 0; i1_inner &lt; 2; ++i1_inner) {
-    for (int i3_inner = 0; i3_inner &lt; 7; ++i3_inner) {
-      compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
-    }
+  for (int i1_inner = 0; i1_inner &lt; 4; ++i1_inner) {
+    compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
+    compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 1)] = max((conv2d_nchw[(i1_inner + 4)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
+    compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 2)] = max((conv2d_nchw[(i1_inner + 8)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
+    compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 3)] = max((conv2d_nchw[(i1_inner + 12)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
+    compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 4)] = max((conv2d_nchw[(i1_inner + 16)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
+    compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 5)] = max((conv2d_nchw[(i1_inner + 20)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
+    compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 6)] = max((conv2d_nchw[(i1_inner + 24)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
   }
 }
 </pre></div>
@@ -1573,7 +2235,7 @@ In the example below we resume the status and do more 5 trials.</p>
 Get devices for measurement successfully!
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes  34.391 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes  41.980 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 8b46539a5f..f0e4e5a595 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -909,7 +909,7 @@ so we can read the log file and load the best schedules.</p>
 Evaluate inference time cost...
 Execution time summary:
  mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)
-   7.8808       7.8798       7.8852       7.8775       0.0032
+   7.8102       7.8081       7.8178       7.8047       0.0055
 </pre></div>
 </div>
 </div>
@@ -931,7 +931,7 @@ to learn how to use the RPC Tracker and RPC Server.
 To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
 with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
 </ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  3.847 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  2.943 seconds)</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-network-cuda-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/eafe360d52540634c9eea0fa89e804bd/tune_network_cuda.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tune_network_cuda.py</span></code></a></p>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
index 609088c551..37fc092a2d 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -928,7 +928,7 @@ so we can read the log file and load the best schedules.</p>
 Evaluate inference time cost...
 Execution time summary:
  mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)
-  766.3268     766.0556     767.4808     765.4441      0.8533
+  761.5435     761.6221     762.6183     760.3901      0.9114
 </pre></div>
 </div>
 </div>
@@ -950,7 +950,7 @@ to learn how to use the RPC Tracker and RPC Server.
 To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
 with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
 </ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  34.721 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  33.775 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 c7ea0b98fc..cc564d2329 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -626,77 +626,77 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
              placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [128, 512], []),
              compute: Buffer(compute_2: Pointer(float32), float32, [128, 512], [])}
   buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute} {
-  for (i0.outer.i1.outer.fused: int32, 0, 256) &quot;parallel&quot; {
-    allocate(compute_3: Pointer(global float32), float32, [256]), storage_scope = global {
-      for (nb_j.inner: int32, 0, 2) {
-        for (i.inner.init: int32, 0, 8) {
-          let cse_var_1: int32 = ((i.inner.init*32) + (nb_j.inner*16))
-           {
-            compute_4: Buffer(compute_3, float32, [256], [])[cse_var_1] = 0f32
-            compute_4[(cse_var_1 + 1)] = 0f32
-            compute_4[(cse_var_1 + 2)] = 0f32
-            compute_4[(cse_var_1 + 3)] = 0f32
-            compute_4[(cse_var_1 + 4)] = 0f32
-            compute_4[(cse_var_1 + 5)] = 0f32
-            compute_4[(cse_var_1 + 6)] = 0f32
-            compute_4[(cse_var_1 + 7)] = 0f32
-            compute_4[(cse_var_1 + 8)] = 0f32
-            compute_4[(cse_var_1 + 9)] = 0f32
-            compute_4[(cse_var_1 + 10)] = 0f32
-            compute_4[(cse_var_1 + 11)] = 0f32
-            compute_4[(cse_var_1 + 12)] = 0f32
-            compute_4[(cse_var_1 + 13)] = 0f32
-            compute_4[(cse_var_1 + 14)] = 0f32
-            compute_4[(cse_var_1 + 15)] = 0f32
-          }
-        }
-        for (elem_idx: int32, 0, let cse_var_2: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_2 + 1)] - placeholder_15[cse_var_2])) {
-          for (i.inner: int32, 0, 8) {
-            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)*2048) + (i.inner*256))
-            let cse_var_17: int32 = (cse_var_20 + 9)
-            let cse_var_16: int32 = (cse_var_20 + 8)
-            let cse_var_15: int32 = (cse_var_20 + 7)
-            let cse_var_14: int32 = (cse_var_20 + 6)
-            let cse_var_13: int32 = (cse_var_20 + 5)
-            let cse_var_12: int32 = (cse_var_20 + 4)
-            let cse_var_11: int32 = (cse_var_20 + 3)
-            let cse_var_10: int32 = (cse_var_20 + 2)
-            let cse_var_9: int32 = (cse_var_20 + 15)
-            let cse_var_8: int32 = (cse_var_20 + 14)
-            let cse_var_7: int32 = (cse_var_20 + 13)
-            let cse_var_6: int32 = (cse_var_20 + 12)
-            let cse_var_5: int32 = (cse_var_20 + 11)
-            let cse_var_4: int32 = (cse_var_20 + 10)
-            let cse_var_3: int32 = (cse_var_20 + 1)
+  for (i0.outer.i1.outer.fused: int32, 0, 32) &quot;parallel&quot; {
+    allocate(compute_3: Pointer(global float32), float32, [2048]), storage_scope = global {
+      for (i.outer.inner: int32, 0, 2) {
+        for (nb_j.inner: int32, 0, 2) {
+          for (i.inner.init: int32, 0, 32) {
+            let cse_var_1: int32 = (((i.outer.inner*1024) + (i.inner.init*32)) + (nb_j.inner*16))
              {
-              compute_4[cse_var_20] = (compute_4[cse_var_20] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[((placeholder_15[cse_var_19]*16) + cse_var_21)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[(cse_var_18 + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_19] + elem_idx)])], 0f32)))
-              compute_4[cse_var_3] = (compute_4[cse_var_3] + (placeholder_16[(((placeholder_15[cse_var_19]*16) + cse_var_21) + 1)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_19] + elem_idx)])], 0f32)))
-              compute_4[cse_var_10] = (compute_4[cse_var_10] + (placeholder_16[(((placeholder_15[cse_var_19]*16) + cse_var_21) + 2)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_19] + elem_idx)])], 0f32)))
-              compute_4[cse_var_11] = (compute_4[cse_var_11] + (placeholder_16[(((placeholder_15[cse_var_19]*16) + cse_var_21) + 3)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_19] + elem_idx)])], 0f32)))
-              compute_4[cse_var_12] = (compute_4[cse_var_12] + (placeholder_16[(((placeholder_15[cse_var_19]*16) + cse_var_21) + 4)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_19] + elem_idx)])], 0f32)))
-              compute_4[cse_var_13] = (compute_4[cse_var_13] + (placeholder_16[(((placeholder_15[cse_var_19]*16) + cse_var_21) + 5)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_19] + elem_idx)])], 0f32)))
-              compute_4[cse_var_14] = (compute_4[cse_var_14] + (placeholder_16[(((placeholder_15[cse_var_19]*16) + cse_var_21) + 6)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_19] + elem_idx)])], 0f32)))
-              compute_4[cse_var_15] = (compute_4[cse_var_15] + (placeholder_16[(((placeholder_15[cse_var_19]*16) + cse_var_21) + 7)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_19] + elem_idx)])], 0f32)))
-              compute_4[cse_var_16] = (compute_4[cse_var_16] + (placeholder_16[(((placeholder_15[cse_var_19]*16) + cse_var_21) + 8)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_19] + elem_idx)])], 0f32)))
-              compute_4[cse_var_17] = (compute_4[cse_var_17] + (placeholder_16[(((placeholder_15[cse_var_19]*16) + cse_var_21) + 9)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_19] + elem_idx)])], 0f32)))
-              compute_4[cse_var_4] = (compute_4[cse_var_4] + (placeholder_16[(((placeholder_15[cse_var_19]*16) + cse_var_21) + 10)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_19] + elem_idx)])], 0f32)))
-              compute_4[cse_var_5] = (compute_4[cse_var_5] + (placeholder_16[(((placeholder_15[cse_var_19]*16) + cse_var_21) + 11)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_19] + elem_idx)])], 0f32)))
-              compute_4[cse_var_6] = (compute_4[cse_var_6] + (placeholder_16[(((placeholder_15[cse_var_19]*16) + cse_var_21) + 12)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_19] + elem_idx)])], 0f32)))
-              compute_4[cse_var_7] = (compute_4[cse_var_7] + (placeholder_16[(((placeholder_15[cse_var_19]*16) + cse_var_21) + 13)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_19] + elem_idx)])], 0f32)))
-              compute_4[cse_var_8] = (compute_4[cse_var_8] + (placeholder_16[(((placeholder_15[cse_var_19]*16) + cse_var_21) + 14)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_19] + elem_idx)])], 0f32)))
-              compute_4[cse_var_9] = (compute_4[cse_var_9] + (placeholder_16[(((placeholder_15[cse_var_19]*16) + cse_var_21) + 15)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_19] + elem_idx)])], 0f32)))
+              compute_4: Buffer(compute_3, float32, [2048], [])[cse_var_1] = 0f32
+              compute_4[(cse_var_1 + 1)] = 0f32
+              compute_4[(cse_var_1 + 2)] = 0f32
+              compute_4[(cse_var_1 + 3)] = 0f32
+              compute_4[(cse_var_1 + 4)] = 0f32
+              compute_4[(cse_var_1 + 5)] = 0f32
+              compute_4[(cse_var_1 + 6)] = 0f32
+              compute_4[(cse_var_1 + 7)] = 0f32
+              compute_4[(cse_var_1 + 8)] = 0f32
+              compute_4[(cse_var_1 + 9)] = 0f32
+              compute_4[(cse_var_1 + 10)] = 0f32
+              compute_4[(cse_var_1 + 11)] = 0f32
+              compute_4[(cse_var_1 + 12)] = 0f32
+              compute_4[(cse_var_1 + 13)] = 0f32
+              compute_4[(cse_var_1 + 14)] = 0f32
+              compute_4[(cse_var_1 + 15)] = 0f32
+            }
+          }
+          for (elem_idx: int32, 0, let cse_var_2: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_2 + 1)] - placeholder_15[cse_var_2])) {
+            for (i.inner: int32, 0, 32) {
+              let cse_var_21: int32 = (elem_idx*16)
+              let cse_var_20: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
+              let cse_var_19: int32 = (((i.outer.inner*1024) + (i.inner*32)) + (nb_j.inner*16))
+              let cse_var_18: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i.outer.inner*8192)) + (i.inner*256))
+              let cse_var_17: int32 = (cse_var_19 + 9)
+              let cse_var_16: int32 = (cse_var_19 + 8)
+              let cse_var_15: int32 = (cse_var_19 + 7)
+              let cse_var_14: int32 = (cse_var_19 + 6)
+              let cse_var_13: int32 = (cse_var_19 + 5)
+              let cse_var_12: int32 = (cse_var_19 + 4)
+              let cse_var_11: int32 = (cse_var_19 + 3)
+              let cse_var_10: int32 = (cse_var_19 + 2)
+              let cse_var_9: int32 = (cse_var_19 + 15)
+              let cse_var_8: int32 = (cse_var_19 + 14)
+              let cse_var_7: int32 = (cse_var_19 + 13)
+              let cse_var_6: int32 = (cse_var_19 + 12)
+              let cse_var_5: int32 = (cse_var_19 + 11)
+              let cse_var_4: int32 = (cse_var_19 + 10)
+              let cse_var_3: int32 = (cse_var_19 + 1)
+               {
+                compute_4[cse_var_19] = (compute_4[cse_var_19] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[((placeholder_15[cse_var_20]*16) + cse_var_21)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[(cse_var_18 + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                compute_4[cse_var_3] = (compute_4[cse_var_3] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                compute_4[cse_var_10] = (compute_4[cse_var_10] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                compute_4[cse_var_11] = (compute_4[cse_var_11] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                compute_4[cse_var_12] = (compute_4[cse_var_12] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                compute_4[cse_var_13] = (compute_4[cse_var_13] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                compute_4[cse_var_14] = (compute_4[cse_var_14] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                compute_4[cse_var_15] = (compute_4[cse_var_15] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                compute_4[cse_var_16] = (compute_4[cse_var_16] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                compute_4[cse_var_17] = (compute_4[cse_var_17] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                compute_4[cse_var_4] = (compute_4[cse_var_4] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                compute_4[cse_var_5] = (compute_4[cse_var_5] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                compute_4[cse_var_6] = (compute_4[cse_var_6] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                compute_4[cse_var_7] = (compute_4[cse_var_7] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                compute_4[cse_var_8] = (compute_4[cse_var_8] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+                compute_4[cse_var_9] = (compute_4[cse_var_9] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+              }
             }
           }
         }
       }
-      for (i0.inner: int32, 0, 8) {
-        for (i1.inner: int32, 0, 32) {
-          let cse_var_22: int32 = ((((floordiv(i0.outer.i1.outer.fused, 16)*4096) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32)) + i1.inner)
-          compute_5: Buffer(compute_2, float32, [65536], [])[cse_var_22] = max((compute_4[((i0.inner*32) + i1.inner)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[cse_var_22]), 0f32)
-        }
+      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_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_22, 1, 32)] = max((compute_4[ramp((i0.inner*32), 1, 32)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
       }
     }
   }
@@ -734,7 +734,7 @@ 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: 1.909 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.727 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 9796736fbe..de95eaa651 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -334,7 +334,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:36.045</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>01:12.272</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 84%" />
@@ -343,7 +343,7 @@
 </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>00:36.008</p></td>
+<td><p>01:12.236</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>
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 8ba4c69dbf..a1c5147ee2 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -683,25 +683,130 @@ Traceback (most recent call last):
   File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 56, in tvm._ffi._cy3.core.tvm_callback
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 875, 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, 2, 4]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 4, 16]), (&#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;, 1)],None,7486054
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 4, 1, 128]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 16, 8]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 0)],None,496972
 No: 2   GFLOPS: 0.00/0.00       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
-    return self.__get_result()
-  File &quot;/usr/lib/python3.7/concurrent/futures/_base.py&quot;, line 384, in __get_result
-    raise self._exception
-  File &quot;/usr/lib/python3.7/concurrent/futures/thread.py&quot;, line 57, in run
-    result = self.fn(*self.args, **self.kwargs)
-  File &quot;/workspace/python/tvm/contrib/popen_pool.py&quot;, line 432, in &lt;lambda&gt;
-    worker = lambda *args: self._worker_run(*args)
-  File &quot;/workspace/python/tvm/contrib/popen_pool.py&quot;, line 401, in _worker_run
-    return proc.recv()
-  File &quot;/workspace/python/tvm/contrib/popen_pool.py&quot;, line 309, in recv
-    raise TimeoutError()
-TimeoutError
-
-        [(&#39;tile_f&#39;, [-1, 1, 1, 2]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 4, 8]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 1)],None,7848555
+  File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 592, 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 544, in _build_func_common
+    func = build(s, args, target_host=task.target_host, runtime=runtime)
+  File &quot;/workspace/python/tvm/driver/build_module.py&quot;, line 227, in build
+    input_mod = lower(inputs, args, name=name, binds=binds)
+  File &quot;/workspace/python/tvm/driver/build_module.py&quot;, line 134, in lower
+    return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+  File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+  File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 276, in tvm._ffi._cy3.core.FuncCall
+  File &quot;tvm/_ffi/_cython/./base.pxi&quot;, line 181, in tvm._ffi._cy3.core.CHECK_CALL
+tvm._ffi.base.TVMError: Traceback (most recent call last):
+  24: TVMFuncCall
+        at ../src/runtime/c_runtime_api.cc:477
+  23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+        at ../include/tvm/runtime/packed_func.h:1217
+  22: Call
+        at ../include/tvm/runtime/packed_func.h:1213
+  21: operator()
+        at ../include/tvm/runtime/packed_func.h:1730
+  20: unpack_call&lt;tvm::IRModule, 5, tvm::&lt;lambda(tvm::te::Schedule, const tvm::runtime::Array&lt;tvm::runtime::ObjectRef&gt;&amp;, const tvm::runtime::String&amp;, const tvm::runtime::Map&lt;tvm::te::Tensor, tvm::tir::Buffer&gt;&amp;, bool)&gt; &gt;
+        at ../include/tvm/runtime/packed_func.h:1670
+  19: run&lt;&gt;
+        at ../include/tvm/runtime/packed_func.h:1630
+  18: run&lt;tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1630
+  17: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1630
+  16: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1630
+  15: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1630
+  14: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1645
+  13: operator()
+        at ../src/driver/driver_api.cc:388
+  12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array&lt;tvm::runtime::ObjectRef, void&gt; const&amp;, std::__cxx11::basic_string&lt;char, std::char_traits&lt;char&gt;, std::allocator&lt;char&gt; &gt; const&amp;, std::unordered_map&lt;tvm::te::Tensor, tvm::tir::Buffer, std::hash&lt;tvm::te::Tensor&gt;, std::equal_to&lt;tvm::te::Tensor&gt;, std::allocator&lt;std::pair&lt;tvm::te::Tensor const, tvm::tir::Buffer&gt; &gt; &gt; const&amp;, tvm::GlobalVarSupply, bool)
+        at ../src/driver/driver_api.cc:374
+  11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array&lt;tvm::transform::Pass, void&gt;)
+        at ../src/driver/driver_api.cc:269
+  10: tvm::transform::Pass::operator()(tvm::IRModule) const
+        at ../src/ir/transform.cc:258
+  9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/ir/transform.cc:274
+  8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/ir/transform.cc:453
+  7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/ir/transform.cc:274
+  6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/tir/ir/transform.cc:100
+  5: tvm::runtime::TypedPackedFunc&lt;tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)&gt;::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+        at ../include/tvm/runtime/packed_func.h:1749
+  4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher&lt;tvm::tir::PrimFunc&gt;::run&lt;tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext&gt;(tvm::runtime::PackedFunc const&amp;, tvm::tir::PrimFunc&amp;&amp;, tvm::IRModule&amp;&amp;, tvm::transform::PassContext&amp;&amp;)
+        at ../include/tvm/runtime/packed_func.h:1693
+  3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()&lt;tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext&gt;(tvm::tir::PrimFunc&amp;&amp;, tvm::IRModule&amp;&amp;, tvm::transform::PassContext&amp;&amp;) const
+        at ../include/tvm/runtime/packed_func.h:1617
+  2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+        at ../include/tvm/runtime/packed_func.h:1217
+  1: Call
+        at ../include/tvm/runtime/packed_func.h:1213
+  0: operator()
+        at ../src/runtime/c_runtime_api.cc:534
+  File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 56, in tvm._ffi._cy3.core.tvm_callback
+  File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 875, in verify_pass
+    raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
+
+Traceback (most recent call last):
+  24: TVMFuncCall
+        at ../src/runtime/c_runtime_api.cc:477
+  23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+        at ../include/tvm/runtime/packed_func.h:1217
+  22: Call
+        at ../include/tvm/runtime/packed_func.h:1213
+  21: operator()
+        at ../include/tvm/runtime/packed_func.h:1730
+  20: unpack_call&lt;tvm::IRModule, 5, tvm::&lt;lambda(tvm::te::Schedule, const tvm::runtime::Array&lt;tvm::runtime::ObjectRef&gt;&amp;, const tvm::runtime::String&amp;, const tvm::runtime::Map&lt;tvm::te::Tensor, tvm::tir::Buffer&gt;&amp;, bool)&gt; &gt;
+        at ../include/tvm/runtime/packed_func.h:1670
+  19: run&lt;&gt;
+        at ../include/tvm/runtime/packed_func.h:1630
+  18: run&lt;tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1630
+  17: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1630
+  16: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1630
+  15: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1630
+  14: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1645
+  13: operator()
+        at ../src/driver/driver_api.cc:388
+  12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array&lt;tvm::runtime::ObjectRef, void&gt; const&amp;, std::__cxx11::basic_string&lt;char, std::char_traits&lt;char&gt;, std::allocator&lt;char&gt; &gt; const&amp;, std::unordered_map&lt;tvm::te::Tensor, tvm::tir::Buffer, std::hash&lt;tvm::te::Tensor&gt;, std::equal_to&lt;tvm::te::Tensor&gt;, std::allocator&lt;std::pair&lt;tvm::te::Tensor const, tvm::tir::Buffer&gt; &gt; &gt; const&amp;, tvm::GlobalVarSupply, bool)
+        at ../src/driver/driver_api.cc:374
+  11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array&lt;tvm::transform::Pass, void&gt;)
+        at ../src/driver/driver_api.cc:269
+  10: tvm::transform::Pass::operator()(tvm::IRModule) const
+        at ../src/ir/transform.cc:258
+  9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/ir/transform.cc:274
+  8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/ir/transform.cc:453
+  7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/ir/transform.cc:274
+  6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/tir/ir/transform.cc:100
+  5: tvm::runtime::TypedPackedFunc&lt;tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)&gt;::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+        at ../include/tvm/runtime/packed_func.h:1749
+  4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher&lt;tvm::tir::PrimFunc&gt;::run&lt;tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext&gt;(tvm::runtime::PackedFunc const&amp;, tvm::tir::PrimFunc&amp;&amp;, tvm::IRModule&amp;&amp;, tvm::transform::PassContext&amp;&amp;)
+        at ../include/tvm/runtime/packed_func.h:1693
+  3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()&lt;tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext&gt;(tvm::tir::PrimFunc&amp;&amp;, tvm::IRModule&amp;&amp;, tvm::transform::PassContext&amp;&amp;) const
+        at ../include/tvm/runtime/packed_func.h:1617
+  2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+        at ../include/tvm/runtime/packed_func.h:1217
+  1: Call
+        at ../include/tvm/runtime/packed_func.h:1213
+  0: operator()
+        at ../src/runtime/c_runtime_api.cc:534
+  File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 56, in tvm._ffi._cy3.core.tvm_callback
+  File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 875, 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, 32, 2, 2]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 1, 16]), (&#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,6896849
 No: 3   GFLOPS: 0.00/0.00       result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 592, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -824,7 +929,7 @@ Traceback (most recent call last):
   File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 56, in tvm._ffi._cy3.core.tvm_callback
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 875, 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, 1]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 7]), (&#39;tile_rc&#39;, [-1, 1, 128]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 0)],None,1143581
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 1, 4, 2]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 64, 4]), (&#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,4347712
 No: 4   GFLOPS: 0.00/0.00       result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 592, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -947,7 +1052,7 @@ Traceback (most recent call last):
   File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 56, in tvm._ffi._cy3.core.tvm_callback
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 875, 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, 2, 16, 2]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 32, 1]), (&#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;, 0)],None,1568686
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 16, 16, 2]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 2, 256]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 1)],None,8706369
 No: 5   GFLOPS: 0.00/0.00       result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 592, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -1070,7 +1175,7 @@ Traceback (most recent call last):
   File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 56, in tvm._ffi._cy3.core.tvm_callback
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 875, 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, 32, 1]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 64, 1]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 1)],None,9896964
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 64, 1, 1]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 128, 4]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 1)],None,5899526
 No: 6   GFLOPS: 0.00/0.00       result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 592, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -1193,10 +1298,254 @@ Traceback (most recent call last):
   File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 56, in tvm._ffi._cy3.core.tvm_callback
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 875, 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, 128, 1]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 1, 2]), (&#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;, 0)],None,810091
-No: 7   GFLOPS: 5.38/5.38       result: MeasureResult(costs=(0.043038143,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.510056734085083, timestamp=1670417483.1694725) [(&#39;tile_f&#39;, [-1, 1, 1, 2]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 8, 16]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 0)],None,324555
-No: 8   GFLOPS: 110.77/110.77   result: MeasureResult(costs=(0.0020900127083333334,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3307535648345947, timestamp=1670417483.8205762)      [(&#39;tile_f&#39;, [-1, 1, 2, 2]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#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, 1]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 0)],None,2169044
-No: 9   GFLOPS: 0.00/110.77     result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 1, 32, 8]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#39;tile_x&#39;, [-1, 1, 1, 7]), (&#39;tile_rc&#39;, [-1, 1, 32]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 0)],None,4016261
+No: 7   GFLOPS: 0.00/0.00       result: Traceback (most recent call last):
+  File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 592, 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 544, in _build_func_common
+    func = build(s, args, target_host=task.target_host, runtime=runtime)
+  File &quot;/workspace/python/tvm/driver/build_module.py&quot;, line 227, in build
+    input_mod = lower(inputs, args, name=name, binds=binds)
+  File &quot;/workspace/python/tvm/driver/build_module.py&quot;, line 134, in lower
+    return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+  File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+  File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 276, in tvm._ffi._cy3.core.FuncCall
+  File &quot;tvm/_ffi/_cython/./base.pxi&quot;, line 181, in tvm._ffi._cy3.core.CHECK_CALL
+tvm._ffi.base.TVMError: Traceback (most recent call last):
+  24: TVMFuncCall
+        at ../src/runtime/c_runtime_api.cc:477
+  23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+        at ../include/tvm/runtime/packed_func.h:1217
+  22: Call
+        at ../include/tvm/runtime/packed_func.h:1213
+  21: operator()
+        at ../include/tvm/runtime/packed_func.h:1730
+  20: unpack_call&lt;tvm::IRModule, 5, tvm::&lt;lambda(tvm::te::Schedule, const tvm::runtime::Array&lt;tvm::runtime::ObjectRef&gt;&amp;, const tvm::runtime::String&amp;, const tvm::runtime::Map&lt;tvm::te::Tensor, tvm::tir::Buffer&gt;&amp;, bool)&gt; &gt;
+        at ../include/tvm/runtime/packed_func.h:1670
+  19: run&lt;&gt;
+        at ../include/tvm/runtime/packed_func.h:1630
+  18: run&lt;tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1630
+  17: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1630
+  16: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1630
+  15: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1630
+  14: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1645
+  13: operator()
+        at ../src/driver/driver_api.cc:388
+  12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array&lt;tvm::runtime::ObjectRef, void&gt; const&amp;, std::__cxx11::basic_string&lt;char, std::char_traits&lt;char&gt;, std::allocator&lt;char&gt; &gt; const&amp;, std::unordered_map&lt;tvm::te::Tensor, tvm::tir::Buffer, std::hash&lt;tvm::te::Tensor&gt;, std::equal_to&lt;tvm::te::Tensor&gt;, std::allocator&lt;std::pair&lt;tvm::te::Tensor const, tvm::tir::Buffer&gt; &gt; &gt; const&amp;, tvm::GlobalVarSupply, bool)
+        at ../src/driver/driver_api.cc:374
+  11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array&lt;tvm::transform::Pass, void&gt;)
+        at ../src/driver/driver_api.cc:269
+  10: tvm::transform::Pass::operator()(tvm::IRModule) const
+        at ../src/ir/transform.cc:258
+  9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/ir/transform.cc:274
+  8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/ir/transform.cc:453
+  7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/ir/transform.cc:274
+  6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/tir/ir/transform.cc:100
+  5: tvm::runtime::TypedPackedFunc&lt;tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)&gt;::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+        at ../include/tvm/runtime/packed_func.h:1749
+  4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher&lt;tvm::tir::PrimFunc&gt;::run&lt;tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext&gt;(tvm::runtime::PackedFunc const&amp;, tvm::tir::PrimFunc&amp;&amp;, tvm::IRModule&amp;&amp;, tvm::transform::PassContext&amp;&amp;)
+        at ../include/tvm/runtime/packed_func.h:1693
+  3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()&lt;tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext&gt;(tvm::tir::PrimFunc&amp;&amp;, tvm::IRModule&amp;&amp;, tvm::transform::PassContext&amp;&amp;) const
+        at ../include/tvm/runtime/packed_func.h:1617
+  2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+        at ../include/tvm/runtime/packed_func.h:1217
+  1: Call
+        at ../include/tvm/runtime/packed_func.h:1213
+  0: operator()
+        at ../src/runtime/c_runtime_api.cc:534
+  File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 56, in tvm._ffi._cy3.core.tvm_callback
+  File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 875, in verify_pass
+    raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
+
+Traceback (most recent call last):
+  24: TVMFuncCall
+        at ../src/runtime/c_runtime_api.cc:477
+  23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+        at ../include/tvm/runtime/packed_func.h:1217
+  22: Call
+        at ../include/tvm/runtime/packed_func.h:1213
+  21: operator()
+        at ../include/tvm/runtime/packed_func.h:1730
+  20: unpack_call&lt;tvm::IRModule, 5, tvm::&lt;lambda(tvm::te::Schedule, const tvm::runtime::Array&lt;tvm::runtime::ObjectRef&gt;&amp;, const tvm::runtime::String&amp;, const tvm::runtime::Map&lt;tvm::te::Tensor, tvm::tir::Buffer&gt;&amp;, bool)&gt; &gt;
+        at ../include/tvm/runtime/packed_func.h:1670
+  19: run&lt;&gt;
+        at ../include/tvm/runtime/packed_func.h:1630
+  18: run&lt;tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1630
+  17: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1630
+  16: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1630
+  15: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1630
+  14: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1645
+  13: operator()
+        at ../src/driver/driver_api.cc:388
+  12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array&lt;tvm::runtime::ObjectRef, void&gt; const&amp;, std::__cxx11::basic_string&lt;char, std::char_traits&lt;char&gt;, std::allocator&lt;char&gt; &gt; const&amp;, std::unordered_map&lt;tvm::te::Tensor, tvm::tir::Buffer, std::hash&lt;tvm::te::Tensor&gt;, std::equal_to&lt;tvm::te::Tensor&gt;, std::allocator&lt;std::pair&lt;tvm::te::Tensor const, tvm::tir::Buffer&gt; &gt; &gt; const&amp;, tvm::GlobalVarSupply, bool)
+        at ../src/driver/driver_api.cc:374
+  11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array&lt;tvm::transform::Pass, void&gt;)
+        at ../src/driver/driver_api.cc:269
+  10: tvm::transform::Pass::operator()(tvm::IRModule) const
+        at ../src/ir/transform.cc:258
+  9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/ir/transform.cc:274
+  8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/ir/transform.cc:453
+  7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/ir/transform.cc:274
+  6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/tir/ir/transform.cc:100
+  5: tvm::runtime::TypedPackedFunc&lt;tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)&gt;::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+        at ../include/tvm/runtime/packed_func.h:1749
+  4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher&lt;tvm::tir::PrimFunc&gt;::run&lt;tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext&gt;(tvm::runtime::PackedFunc const&amp;, tvm::tir::PrimFunc&amp;&amp;, tvm::IRModule&amp;&amp;, tvm::transform::PassContext&amp;&amp;)
+        at ../include/tvm/runtime/packed_func.h:1693
+  3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()&lt;tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext&gt;(tvm::tir::PrimFunc&amp;&amp;, tvm::IRModule&amp;&amp;, tvm::transform::PassContext&amp;&amp;) const
+        at ../include/tvm/runtime/packed_func.h:1617
+  2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+        at ../include/tvm/runtime/packed_func.h:1217
+  1: Call
+        at ../include/tvm/runtime/packed_func.h:1213
+  0: operator()
+        at ../src/runtime/c_runtime_api.cc:534
+  File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 56, in tvm._ffi._cy3.core.tvm_callback
+  File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 875, 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, 1, 4, 128]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 32, 2]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 1)],None,8959715
+No: 8   GFLOPS: 0.00/0.00       result: Traceback (most recent call last):
+  File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 592, 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 544, in _build_func_common
+    func = build(s, args, target_host=task.target_host, runtime=runtime)
+  File &quot;/workspace/python/tvm/driver/build_module.py&quot;, line 227, in build
+    input_mod = lower(inputs, args, name=name, binds=binds)
+  File &quot;/workspace/python/tvm/driver/build_module.py&quot;, line 134, in lower
+    return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+  File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+  File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 276, in tvm._ffi._cy3.core.FuncCall
+  File &quot;tvm/_ffi/_cython/./base.pxi&quot;, line 181, in tvm._ffi._cy3.core.CHECK_CALL
+tvm._ffi.base.TVMError: Traceback (most recent call last):
+  24: TVMFuncCall
+        at ../src/runtime/c_runtime_api.cc:477
+  23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+        at ../include/tvm/runtime/packed_func.h:1217
+  22: Call
+        at ../include/tvm/runtime/packed_func.h:1213
+  21: operator()
+        at ../include/tvm/runtime/packed_func.h:1730
+  20: unpack_call&lt;tvm::IRModule, 5, tvm::&lt;lambda(tvm::te::Schedule, const tvm::runtime::Array&lt;tvm::runtime::ObjectRef&gt;&amp;, const tvm::runtime::String&amp;, const tvm::runtime::Map&lt;tvm::te::Tensor, tvm::tir::Buffer&gt;&amp;, bool)&gt; &gt;
+        at ../include/tvm/runtime/packed_func.h:1670
+  19: run&lt;&gt;
+        at ../include/tvm/runtime/packed_func.h:1630
+  18: run&lt;tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1630
+  17: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1630
+  16: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1630
+  15: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1630
+  14: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1645
+  13: operator()
+        at ../src/driver/driver_api.cc:388
+  12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array&lt;tvm::runtime::ObjectRef, void&gt; const&amp;, std::__cxx11::basic_string&lt;char, std::char_traits&lt;char&gt;, std::allocator&lt;char&gt; &gt; const&amp;, std::unordered_map&lt;tvm::te::Tensor, tvm::tir::Buffer, std::hash&lt;tvm::te::Tensor&gt;, std::equal_to&lt;tvm::te::Tensor&gt;, std::allocator&lt;std::pair&lt;tvm::te::Tensor const, tvm::tir::Buffer&gt; &gt; &gt; const&amp;, tvm::GlobalVarSupply, bool)
+        at ../src/driver/driver_api.cc:374
+  11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array&lt;tvm::transform::Pass, void&gt;)
+        at ../src/driver/driver_api.cc:269
+  10: tvm::transform::Pass::operator()(tvm::IRModule) const
+        at ../src/ir/transform.cc:258
+  9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/ir/transform.cc:274
+  8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/ir/transform.cc:453
+  7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/ir/transform.cc:274
+  6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/tir/ir/transform.cc:100
+  5: tvm::runtime::TypedPackedFunc&lt;tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)&gt;::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+        at ../include/tvm/runtime/packed_func.h:1749
+  4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher&lt;tvm::tir::PrimFunc&gt;::run&lt;tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext&gt;(tvm::runtime::PackedFunc const&amp;, tvm::tir::PrimFunc&amp;&amp;, tvm::IRModule&amp;&amp;, tvm::transform::PassContext&amp;&amp;)
+        at ../include/tvm/runtime/packed_func.h:1693
+  3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()&lt;tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext&gt;(tvm::tir::PrimFunc&amp;&amp;, tvm::IRModule&amp;&amp;, tvm::transform::PassContext&amp;&amp;) const
+        at ../include/tvm/runtime/packed_func.h:1617
+  2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+        at ../include/tvm/runtime/packed_func.h:1217
+  1: Call
+        at ../include/tvm/runtime/packed_func.h:1213
+  0: operator()
+        at ../src/runtime/c_runtime_api.cc:534
+  File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 56, in tvm._ffi._cy3.core.tvm_callback
+  File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 875, in verify_pass
+    raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
+
+Traceback (most recent call last):
+  24: TVMFuncCall
+        at ../src/runtime/c_runtime_api.cc:477
+  23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+        at ../include/tvm/runtime/packed_func.h:1217
+  22: Call
+        at ../include/tvm/runtime/packed_func.h:1213
+  21: operator()
+        at ../include/tvm/runtime/packed_func.h:1730
+  20: unpack_call&lt;tvm::IRModule, 5, tvm::&lt;lambda(tvm::te::Schedule, const tvm::runtime::Array&lt;tvm::runtime::ObjectRef&gt;&amp;, const tvm::runtime::String&amp;, const tvm::runtime::Map&lt;tvm::te::Tensor, tvm::tir::Buffer&gt;&amp;, bool)&gt; &gt;
+        at ../include/tvm/runtime/packed_func.h:1670
+  19: run&lt;&gt;
+        at ../include/tvm/runtime/packed_func.h:1630
+  18: run&lt;tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1630
+  17: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1630
+  16: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1630
+  15: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1630
+  14: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1645
+  13: operator()
+        at ../src/driver/driver_api.cc:388
+  12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array&lt;tvm::runtime::ObjectRef, void&gt; const&amp;, std::__cxx11::basic_string&lt;char, std::char_traits&lt;char&gt;, std::allocator&lt;char&gt; &gt; const&amp;, std::unordered_map&lt;tvm::te::Tensor, tvm::tir::Buffer, std::hash&lt;tvm::te::Tensor&gt;, std::equal_to&lt;tvm::te::Tensor&gt;, std::allocator&lt;std::pair&lt;tvm::te::Tensor const, tvm::tir::Buffer&gt; &gt; &gt; const&amp;, tvm::GlobalVarSupply, bool)
+        at ../src/driver/driver_api.cc:374
+  11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array&lt;tvm::transform::Pass, void&gt;)
+        at ../src/driver/driver_api.cc:269
+  10: tvm::transform::Pass::operator()(tvm::IRModule) const
+        at ../src/ir/transform.cc:258
+  9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/ir/transform.cc:274
+  8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/ir/transform.cc:453
+  7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/ir/transform.cc:274
+  6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/tir/ir/transform.cc:100
+  5: tvm::runtime::TypedPackedFunc&lt;tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)&gt;::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+        at ../include/tvm/runtime/packed_func.h:1749
+  4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher&lt;tvm::tir::PrimFunc&gt;::run&lt;tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext&gt;(tvm::runtime::PackedFunc const&amp;, tvm::tir::PrimFunc&amp;&amp;, tvm::IRModule&amp;&amp;, tvm::transform::PassContext&amp;&amp;)
+        at ../include/tvm/runtime/packed_func.h:1693
+  3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()&lt;tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext&gt;(tvm::tir::PrimFunc&amp;&amp;, tvm::IRModule&amp;&amp;, tvm::transform::PassContext&amp;&amp;) const
+        at ../include/tvm/runtime/packed_func.h:1617
+  2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+        at ../include/tvm/runtime/packed_func.h:1217
+  1: Call
+        at ../include/tvm/runtime/packed_func.h:1213
+  0: operator()
+        at ../src/runtime/c_runtime_api.cc:534
+  File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 56, in tvm._ffi._cy3.core.tvm_callback
+  File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 875, 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, 4, 1]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 7, 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;, 1500), (&#39;unroll_explicit&#39;, 0)],None,3668746
+No: 9   GFLOPS: 0.00/0.00       result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 592, 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 544, in _build_func_common
@@ -1318,9 +1667,8 @@ Traceback (most recent call last):
   File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 56, in tvm._ffi._cy3.core.tvm_callback
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 875, 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, 16, 1]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 7]), (&#39;tile_rc&#39;, [-1, 1, 32]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 1)],None,10017078
-No: 10  GFLOPS: 1.09/110.77     result: MeasureResult(costs=(0.212369934,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.9424479007720947, timestamp=1670417487.958273) [(&#39;tile_f&#39;, [-1, 16, 1, 16]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 1, 1]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 0)],None,2517188
-No: 11  GFLOPS: 0.00/110.77     result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 2, 2, 64]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 1, 128]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 1)],None,5789285
+No: 10  GFLOPS: 0.00/0.00       result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 592, 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 544, in _build_func_common
@@ -1442,8 +1790,8 @@ Traceback (most recent call last):
   File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 56, in tvm._ffi._cy3.core.tvm_callback
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 875, 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, 2, 4]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 4, 128]), (&#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,4441252
-No: 12  GFLOPS: 0.00/110.77     result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 8, 32, 2]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 7]), (&#39;tile_rc&#39;, [-1, 4, 8]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 1)],None,8429833
+No: 11  GFLOPS: 0.00/0.00       result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 592, 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 544, in _build_func_common
@@ -1565,8 +1913,8 @@ Traceback (most recent call last):
   File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 56, in tvm._ffi._cy3.core.tvm_callback
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 875, 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, 8, 2, 8]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 1, 512]), (&#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,6966446
-No: 13  GFLOPS: 0.00/110.77     result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 1, 128, 1]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 2, 64]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 1)],None,9456749
+No: 12  GFLOPS: 0.00/0.00       result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 592, 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 544, in _build_func_common
@@ -1688,8 +2036,8 @@ Traceback (most recent call last):
   File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 56, in tvm._ffi._cy3.core.tvm_callback
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 875, 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, 1, 16, 1]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 7]), (&#39;tile_rc&#39;, [-1, 2, 64]), (&#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,6166414
-No: 14  GFLOPS: 0.00/110.77     result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 32, 1, 4]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 1, 128]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 1)],None,8886785
+No: 13  GFLOPS: 0.00/0.00       result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 592, 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 544, in _build_func_common
@@ -1811,8 +2159,8 @@ Traceback (most recent call last):
   File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 56, in tvm._ffi._cy3.core.tvm_callback
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 875, 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, 8, 2, 4]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 8, 8]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 1)],None,8626311
-No: 15  GFLOPS: 0.00/110.77     result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 8, 4, 16]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 32, 8]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 1)],None,5921258
+No: 14  GFLOPS: 0.00/0.00       result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 592, 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 544, in _build_func_common
@@ -1934,8 +2282,8 @@ Traceback (most recent call last):
   File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 56, in tvm._ffi._cy3.core.tvm_callback
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 875, 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, 2, 16, 8]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 1, 512]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 0)],None,3869079
-No: 16  GFLOPS: 0.00/110.77     result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 2, 32, 4]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 7]), (&#39;tile_rc&#39;, [-1, 64, 1]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 0)],None,1960111
+No: 15  GFLOPS: 0.00/0.00       result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 592, 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 544, in _build_func_common
@@ -2057,8 +2405,8 @@ Traceback (most recent call last):
   File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 56, in tvm._ffi._cy3.core.tvm_callback
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 875, 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, 1, 2]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 4, 64]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 1)],None,7136417
-No: 17  GFLOPS: 0.00/110.77     result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 1, 8, 8]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 256, 1]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 0)],None,1965854
+No: 16  GFLOPS: 0.00/0.00       result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 592, 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 544, in _build_func_common
@@ -2180,8 +2528,9 @@ Traceback (most recent call last):
   File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 56, in tvm._ffi._cy3.core.tvm_callback
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 875, 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, 16]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 1, 256]), (&#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,5218577
-No: 18  GFLOPS: 0.00/110.77     result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 16, 8, 4]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 7]), (&#39;tile_rc&#39;, [-1, 128, 2]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 0)],None,643625
+No: 17  GFLOPS: 1.83/1.83       result: MeasureResult(costs=(0.126615013,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7828867435455322, timestamp=1670437283.4448225)        [(&#39;tile_f&#39;, [-1, 1, 1, 64]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 7]), (&#39;tile_rc&#39;, [-1, 2, 2]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 0)],None,1396760
+No: 18  GFLOPS: 0.00/1.83       result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 592, 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 544, in _build_func_common
@@ -2303,8 +2652,8 @@ Traceback (most recent call last):
   File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 56, in tvm._ffi._cy3.core.tvm_callback
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 875, 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, 1, 64]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 32, 16]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 1)],None,5559162
-No: 19  GFLOPS: 0.00/110.77     result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 64, 4, 2]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 256, 1]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 0)],None,2739078
+No: 19  GFLOPS: 0.00/1.83       result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 592, 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 544, in _build_func_common
@@ -2426,8 +2775,8 @@ Traceback (most recent call last):
   File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 56, in tvm._ffi._cy3.core.tvm_callback
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 875, 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, 32, 2, 4]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 4, 128]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 0)],None,3665533
-No: 20  GFLOPS: 0.00/110.77     result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 8, 2, 1]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 7]), (&#39;tile_rc&#39;, [-1, 1, 256]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 1)],None,7349113
+No: 20  GFLOPS: 0.00/1.83       result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 592, 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 544, in _build_func_common
@@ -2549,7 +2898,7 @@ Traceback (most recent call last):
   File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 56, in tvm._ffi._cy3.core.tvm_callback
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 875, 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, 2, 16, 2]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 1, 64]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 0)],None,2096906
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 4, 2, 8]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 64, 1]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 0)],None,2538065
 </pre></div>
 </div>
 <p>Finally we can inspect the best config from log file, check correctness,
@@ -2588,11 +2937,12 @@ and measure running time.</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Finish loading 20 records
 
 Best config:
-[(&#39;tile_f&#39;, [-1, 1, 2, 2]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#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, 1]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 0)],None,2169044
+[(&#39;tile_f&#39;, [-1, 1, 1, 64]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 7]), (&#39;tile_rc&#39;, [-1, 2, 2]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 0)],None,1396760
 Finish loading 20 records
-Time cost of this operator: 0.002487
+Time cost of this operator: 0.127007
 </pre></div>
 </div>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  12.236 seconds)</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autotvm-tune-conv2d-cuda-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/6ad550da5092845382b1197f58a93816/tune_conv2d_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_cuda.py</span></code></a></p>
diff --git a/docs/how_to/work_with_microtvm/micro_autotune.html b/docs/how_to/work_with_microtvm/micro_autotune.html
index 8cb6009406..e5d5dd2b5e 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -592,10 +592,10 @@ the tuned operator.</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build without Autotuning ##########
 Node Name                                     Ops                                           Time(us)  Time(%)  Shape              Inputs  Outputs  Measurements(us)
 ---------                                     ---                                           --------  -------  -----              ------  -------  ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  311.8     98.721   (1, 2, 10, 10, 3)  2       1        [311.8]
-tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       3.068     0.971    (1, 6, 10, 10)     1       1        [3.068]
-tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.973     0.308    (1, 1, 10, 10, 3)  1       1        [0.973]
-Total_time                                    -                                             315.841   -        -                  -       -        -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  308.9     98.713   (1, 2, 10, 10, 3)  2       1        [308.9]
+tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       3.049     0.974    (1, 6, 10, 10)     1       1        [3.049]
+tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.978     0.313    (1, 1, 10, 10, 3)  1       1        [0.978]
+Total_time                                    -                                             312.927   -        -                  -       -        -
 </pre></div>
 </div>
 </div>
@@ -647,10 +647,10 @@ Total_time                                    -
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build with Autotuning ##########
 Node Name                                     Ops                                           Time(us)  Time(%)  Shape              Inputs  Outputs  Measurements(us)
 ---------                                     ---                                           --------  -------  -----              ------  -------  ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  102.6     97.431   (1, 6, 10, 10, 1)  2       1        [102.6]
-tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       1.806     1.715    (1, 6, 10, 10)     1       1        [1.806]
-tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.899     0.854    (1, 3, 10, 10, 1)  1       1        [0.899]
-Total_time                                    -                                             105.306   -        -                  -       -        -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  104.6     97.484   (1, 6, 10, 10, 1)  2       1        [104.6]
+tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       1.772     1.651    (1, 6, 10, 10)     1       1        [1.772]
+tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.929     0.865    (1, 3, 10, 10, 1)  1       1        [0.929]
+Total_time                                    -                                             107.3     -        -                  -       -        -
 </pre></div>
 </div>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/micro_pytorch.html b/docs/how_to/work_with_microtvm/micro_pytorch.html
index 778b75c371..1b94a5d423 100644
--- a/docs/how_to/work_with_microtvm/micro_pytorch.html
+++ b/docs/how_to/work_with_microtvm/micro_pytorch.html
@@ -434,8 +434,7 @@ download a cat image and preprocess it to use as the model input.</p>
 Downloading: &quot;https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth&quot; to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
 
   0%|          | 0.00/3.42M [00:00&lt;?, ?B/s]
- 92%|#########2| 3.16M/3.42M [00:00&lt;00:00, 33.2MB/s]
-100%|##########| 3.42M/3.42M [00:00&lt;00:00, 35.3MB/s]
+100%|##########| 3.42M/3.42M [00:00&lt;00:00, 60.4MB/s]
 /workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
   return LooseVersion(torch_ver) &gt; ver
 /venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -559,7 +558,7 @@ via the host <cite>main.cc`</cite> or if a Zephyr emulated board is selected as
 Torch top-1 id: 282, class name: tiger cat
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  5.621 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  6.930 seconds)</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-pytorch-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/12b9ecc04c41abaa12022061771821d1/micro_pytorch.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">micro_pytorch.py</span></code></a></p>
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index 3c0e80e964..af7af7cb2e 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -524,7 +524,7 @@ take about <strong>2 minutes</strong> to download the Stanford Cars, while COCO
 <a href="https://docs.python.org/3/library/shutil.html#shutil.move" title="shutil.move" class="sphx-glr-backref-module-shutil sphx-glr-backref-type-py-function"><span class="n">shutil</span><span class="o">.</span><span class="n">move</span></a><span class="p">(</span><span class="sa">f</span><span class="s2">&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/tmp0_hnp3bf/images/random&#39;
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>&#39;/tmp/tmp2ds93y81/images/random&#39;
 </pre></div>
 </div>
 </div>
@@ -584,8 +584,8 @@ objects to other stuff? We can display some examples from our datasets using <co
     <span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">&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], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [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/tmp0_hnp3bf/images/target contains 8144 images
-/tmp/tmp0_hnp3bf/images/random contains 5000 images
+<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmp2ds93y81/images/target contains 8144 images
+/tmp/tmp2ds93y81/images/random contains 5000 images
 </pre></div>
 </div>
 </div>
@@ -697,13 +697,13 @@ the time on our validation set).</p>
 </pre></div>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 47s - loss: 0.2188 - accuracy: 0.9246 - val_loss: 0.1096 - val_accuracy: 0.9615 - 47s/epoch - 144ms/step
+328/328 - 48s - loss: 0.2211 - accuracy: 0.9244 - val_loss: 0.1686 - val_accuracy: 0.9471 - 48s/epoch - 146ms/step
 Epoch 2/3
-328/328 - 44s - loss: 0.0977 - accuracy: 0.9656 - val_loss: 0.1007 - val_accuracy: 0.9634 - 44s/epoch - 133ms/step
+328/328 - 44s - loss: 0.0972 - accuracy: 0.9629 - val_loss: 0.1509 - val_accuracy: 0.9494 - 44s/epoch - 133ms/step
 Epoch 3/3
-328/328 - 43s - loss: 0.0615 - accuracy: 0.9754 - val_loss: 0.1930 - val_accuracy: 0.9407 - 43s/epoch - 132ms/step
+328/328 - 43s - loss: 0.0732 - accuracy: 0.9720 - val_loss: 0.1112 - val_accuracy: 0.9634 - 43s/epoch - 133ms/step
 
-&lt;keras.callbacks.History object at 0x7fbf0f4b6ad0&gt;
+&lt;keras.callbacks.History object at 0x7faf16f55c90&gt;
 </pre></div>
 </div>
 </div>
@@ -965,7 +965,7 @@ as intended.</p>
 <p>From here, we could modify the model to read live images from the camera - we have another
 Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
 <a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes  51.632 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes  48.393 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 e6a011be93..d0a54add56 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -334,7 +334,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>07:00.997</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>07:00.335</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 83%" />
@@ -343,23 +343,23 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>04:51.632</p></td>
+<td><p>04:48.393</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="micro_pytorch.html#sphx-glr-how-to-work-with-microtvm-micro-pytorch-py"><span class="std std-ref">microTVM PyTorch Tutorial</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_pytorch.py</span></code>)</p></td>
-<td><p>01:05.621</p></td>
+<td><p>01:06.930</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:51.841</p></td>
+<td><p>00:52.473</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="micro_aot.html#sphx-glr-how-to-work-with-microtvm-micro-aot-py"><span class="std std-ref">microTVM Host-Driven AoT</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:08.011</p></td>
+<td><p>00:08.590</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:03.889</p></td>
+<td><p>00:03.946</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="micro_reference_vm.html#sphx-glr-how-to-work-with-microtvm-micro-reference-vm-py"><span class="std std-ref">microTVM Reference Virtual Machines</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_reference_vm.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_relay/sg_execution_times.html b/docs/how_to/work_with_relay/sg_execution_times.html
index e8bfe95491..75ba8429ca 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -334,7 +334,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:45.683</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:45.258</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 84%" />
@@ -343,15 +343,15 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="using_pipeline_executor.html#sphx-glr-how-to-work-with-relay-using-pipeline-executor-py"><span class="std std-ref">Using Pipeline Executor in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_pipeline_executor.py</span></code>)</p></td>
-<td><p>00:33.210</p></td>
+<td><p>00:33.194</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></td>
-<td><p>00:10.878</p></td>
+<td><p>00:10.412</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>00:01.588</p></td>
+<td><p>00:01.645</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 436e47531f..188e83f768 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -529,7 +529,7 @@ The following example customizes CUDA lowering rule for <code class="code docuti
 <a href="../../reference/api/python/ir.html#tvm.ir.register_intrin_lowering" title="tvm.ir.register_intrin_lowering" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-function"><span class="n">register_intrin_lowering</span></a><span class="p">(</span><span class="s2">&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 0x7fbf0af96c20&gt;
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>&lt;function my_cuda_math_rule at 0x7faf16a00c20&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 3466ee3c41..6aa29a314f 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -334,7 +334,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:08.287</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:08.565</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 83%" />
@@ -343,19 +343,19 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:05.744</p></td>
+<td><p>00:05.996</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="tensorize.html#sphx-glr-how-to-work-with-schedules-tensorize-py"><span class="std std-ref">Use Tensorize to Leverage Hardware Intrinsics</span></a> (<code class="docutils literal notranslate"><span class="pre">tensorize.py</span></code>)</p></td>
-<td><p>00:01.163</p></td>
+<td><p>00:01.193</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>00:00.590</p></td>
+<td><p>00:00.589</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>00:00.570</p></td>
+<td><p>00:00.568</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>
@@ -363,7 +363,7 @@
 <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>00:00.052</p></td>
+<td><p>00:00.051</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 d3a4e89b95..a2b9eadf8f 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -580,7 +580,7 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
              B: Buffer(B_2: Pointer(float32), float32, [512, 64], []),
              C: Buffer(C_2: Pointer(float32), float32, [1024, 512], [])}
   buffer_map = {A_1: A, B_1: B, C_1: C} {
-  attr [IterVar(i: int32, (nullptr), &quot;DataPar&quot;, &quot;&quot;)] &quot;pragma_import_llvm&quot; = &quot;; ModuleID = &#39;/tmp/tmp14058akj/input0.cc&#39;\nsource_filename = \&quot;/tmp/tmp14058akj/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/tmpyo6f510p/input0.cc&#39;\nsource_filename = \&quot;/tmp/tmpyo6f510p/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 705ee620df..8d4004f4e4 100644
--- a/docs/install/nnpack.html
+++ b/docs/install/nnpack.html
@@ -229,17 +229,7 @@
               <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 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="from_source.html">Install from Source</a></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/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 3c83280bab..1c99d6be5b 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1609,7 +1609,7 @@ history states as starting point to perform Evolutionary Search).</p></li>
 
 <dl class="py class">
 <dt class="sig sig-object py" id="tvm.auto_scheduler.SketchPolicy">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
 <dd><p>The search policy that searches in a hierarchical search space defined by sketches.
 The policy randomly samples programs from the space defined by sketches and use evolutionary
 search to fine-tune them.</p>
@@ -1893,7 +1893,7 @@ Candidates:
 
 <dl class="py function">
 <dt class="sig sig-object py" id="tvm.auto_scheduler.auto_schedule">
-<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
 <dd><p>THIS API IS DEPRECATED.</p>
 <p>Run auto scheduling search for a task.</p>
 <dl class="field-list simple">
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index b216a07fce..88a9b731fc 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/eda84e780/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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 5dfa4bf6fe..62c169e825 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/eda84e780/web/src/memory.ts#L223">memory.ts:223</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/memory.ts#L208">memory.ts:208</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/memory.ts#L312">memory.ts:312</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/memory.ts#L284">memory.ts:284</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/memory.ts#L388">memory.ts:388</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/memory.ts#L376">memory.ts:376</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/memory.ts#L267">memory.ts:267</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/memory.ts#L243">memory.ts:243</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/memory.ts#L321">memory.ts:321</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/memory.ts#L252">memory.ts:252</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/memory.ts#L359">memory.ts:359</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/memory.ts#L342">memory.ts:342</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/memory.ts#L350">memory.ts:350</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/memory.ts#L326">memory.ts:326</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/memory.ts#L363">memory.ts:363</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/memory.ts#L346">memory.ts:346</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/memory.ts#L334">memory.ts:334</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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 a1b863708f..d8cebfc642 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/eda84e780/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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 1e0bd51684..ae82041920 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/eda84e780/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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 4bb7e40861..13746160f4 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/eda84e780/web/src/environment.ts#L86">environment.ts:86</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/environment.ts#L70">environment.ts:70</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/environment.ts#L69">environment.ts:69</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/environment.ts#L78">environment.ts:78</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/environment.ts#L84">environment.ts:84</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/environment.ts#L105">environment.ts:105</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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 df845a6b7f..2d88dfe28b 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/eda84e780/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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 17e3c15224..9d96866001 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/eda84e780/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/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/eda84e780/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/f674e12d1/web/src/runtime.ts#L644">runtime.ts:644</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
... 2405 lines suppressed ...