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 2022/08/04 22:54:37 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@2866f315f9899a49917e1a9adda21fc15841ee55)

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 92f4eaa66 deploying docs (apache/tvm@2866f315f9899a49917e1a9adda21fc15841ee55)
92f4eaa66 is described below

commit 92f4eaa66eca295c182009038f877e5fe93589b8
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Thu Aug 4 22:54:31 2022 +0000

    deploying docs (apache/tvm@2866f315f9899a49917e1a9adda21fc15841ee55)
---
 .../how_to/compile_models/from_darknet.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_android.rst.txt  |   2 +-
 .../deploy_object_detection_pytorch.rst.txt        |   4 +-
 .../deploy_models/deploy_prequantized.rst.txt      |   6 +-
 .../deploy_prequantized_tflite.rst.txt             |   4 +-
 .../how_to/deploy_models/deploy_quantized.rst.txt  |   2 +-
 .../deploy_models/deploy_ssd_gluoncv.rst.txt       |   4 +-
 .../deploy_models/sg_execution_times.rst.txt       |  18 +-
 .../extend_tvm/bring_your_own_datatypes.rst.txt    |   4 +-
 .../how_to/extend_tvm/sg_execution_times.rst.txt   |   6 +-
 .../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                 | 927 +++------------------
 .../tune_network_cuda.rst.txt                      |   2 +-
 .../tune_network_x86.rst.txt                       |   4 +-
 .../tune_sparse_x86.rst.txt                        | 104 ++-
 .../tune_with_autotvm/sg_execution_times.rst.txt   |   6 +-
 .../tune_with_autotvm/tune_conv2d_cuda.rst.txt     |  26 +-
 .../work_with_microtvm/micro_autotune.rst.txt      |  16 +-
 .../how_to/work_with_microtvm/micro_train.rst.txt  |  16 +-
 .../work_with_microtvm/sg_execution_times.rst.txt  |  10 +-
 .../work_with_relay/sg_execution_times.rst.txt     |   8 +-
 .../how_to/work_with_schedules/intrin_math.rst.txt |   2 +-
 .../work_with_schedules/sg_execution_times.rst.txt |  12 +-
 .../how_to/work_with_schedules/tensorize.rst.txt   |   2 +-
 .../tutorials/autotvm/sg_execution_times.rst.txt   |   4 +-
 .../frontend/deploy_classification.rst.txt         |   2 +-
 .../tutorials/frontend/deploy_detection.rst.txt    |   2 +-
 .../tutorials/frontend/sg_execution_times.rst.txt  |   6 +-
 .../tutorials/optimize/sg_execution_times.rst.txt  |   6 +-
 .../topic/vta/tutorials/sg_execution_times.rst.txt |   6 +-
 .../tutorial/auto_scheduler_matmul_x86.rst.txt     |   2 +-
 docs/_sources/tutorial/autotvm_matmul_x86.rst.txt  |  20 +-
 docs/_sources/tutorial/autotvm_relay_x86.rst.txt   |  54 +-
 .../tutorial/cross_compilation_and_rpc.rst.txt     |   2 +-
 docs/_sources/tutorial/intro_topi.rst.txt          |   2 +-
 docs/_sources/tutorial/sg_execution_times.rst.txt  |  22 +-
 .../tutorial/tensor_expr_get_started.rst.txt       |  51 +-
 docs/commit_hash                                   |   2 +-
 docs/how_to/compile_models/from_darknet.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       |   6 +-
 docs/how_to/compile_models/from_tensorflow.html    |   2 +-
 docs/how_to/compile_models/sg_execution_times.html |  30 +-
 .../deploy_models/deploy_model_on_android.html     |   2 +-
 .../deploy_object_detection_pytorch.html           |  20 +-
 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  |  35 +-
 docs/how_to/deploy_models/sg_execution_times.html  |  18 +-
 .../extend_tvm/bring_your_own_datatypes.html       |   4 +-
 docs/how_to/extend_tvm/sg_execution_times.html     |   6 +-
 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                    | 927 +++------------------
 .../tune_with_autoscheduler/tune_network_cuda.html |   2 +-
 .../tune_with_autoscheduler/tune_network_x86.html  |   4 +-
 .../tune_with_autoscheduler/tune_sparse_x86.html   | 104 ++-
 .../tune_with_autotvm/sg_execution_times.html      |   6 +-
 .../how_to/tune_with_autotvm/tune_conv2d_cuda.html |  26 +-
 docs/how_to/work_with_microtvm/micro_autotune.html |  16 +-
 docs/how_to/work_with_microtvm/micro_train.html    |  16 +-
 .../work_with_microtvm/sg_execution_times.html     |  10 +-
 .../how_to/work_with_relay/sg_execution_times.html |   8 +-
 docs/how_to/work_with_schedules/intrin_math.html   |   2 +-
 .../work_with_schedules/sg_execution_times.html    |  12 +-
 docs/how_to/work_with_schedules/tensorize.html     |   2 +-
 docs/reference/api/python/auto_scheduler.html      |   4 +-
 .../api/typedoc/classes/bytestreamreader.html      |  12 +-
 .../api/typedoc/classes/cachedcallstack.html       |  34 +-
 docs/reference/api/typedoc/classes/dldatatype.html |  12 +-
 docs/reference/api/typedoc/classes/dldevice.html   |  10 +-
 .../reference/api/typedoc/classes/environment.html |  12 +-
 docs/reference/api/typedoc/classes/ffilibrary.html |  20 +-
 .../api/typedoc/classes/graphexecutor.html         |  16 +-
 docs/reference/api/typedoc/classes/instance.html   |  40 +-
 docs/reference/api/typedoc/classes/memory.html     |  34 +-
 docs/reference/api/typedoc/classes/module.html     |  10 +-
 docs/reference/api/typedoc/classes/ndarray.html    |  22 +-
 .../api/typedoc/classes/packedfunccell.html        |   6 +-
 docs/reference/api/typedoc/classes/rpcserver.html  |  14 +-
 docs/reference/api/typedoc/classes/scalar.html     |   6 +-
 .../api/typedoc/classes/webgpucontext.html         |  12 +-
 docs/reference/api/typedoc/enums/argtypecode.html  |  30 +-
 .../api/typedoc/enums/aynccallbackcode.html        |   4 +-
 .../api/typedoc/enums/dldatatypecode.html          |   8 +-
 .../api/typedoc/enums/rpcserverstate.html          |  12 +-
 docs/reference/api/typedoc/enums/sizeof.html       |  18 +-
 docs/reference/api/typedoc/index.html              | 112 +--
 .../api/typedoc/interfaces/disposable.html         |   2 +-
 .../api/typedoc/interfaces/functioninfo.html       |   6 +-
 .../api/typedoc/interfaces/libraryprovider.html    |   4 +-
 docs/searchindex.js                                |   2 +-
 .../vta/tutorials/autotvm/sg_execution_times.html  |   4 +-
 .../tutorials/frontend/deploy_classification.html  |   2 +-
 .../vta/tutorials/frontend/deploy_detection.html   |   2 +-
 .../vta/tutorials/frontend/sg_execution_times.html |   6 +-
 .../vta/tutorials/optimize/sg_execution_times.html |   6 +-
 docs/topic/vta/tutorials/sg_execution_times.html   |   6 +-
 docs/tutorial/auto_scheduler_matmul_x86.html       |   2 +-
 docs/tutorial/autotvm_matmul_x86.html              |  20 +-
 docs/tutorial/autotvm_relay_x86.html               | 258 +++---
 docs/tutorial/cross_compilation_and_rpc.html       |   2 +-
 docs/tutorial/intro_topi.html                      |   2 +-
 docs/tutorial/sg_execution_times.html              |  26 +-
 docs/tutorial/tensor_expr_get_started.html         |  47 +-
 121 files changed, 1227 insertions(+), 2422 deletions(-)

diff --git a/docs/_sources/how_to/compile_models/from_darknet.rst.txt b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
index 6864d9aba..281d48d48 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -317,7 +317,7 @@ The process is no different from other examples.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  1.434 seconds)
+   **Total running time of the script:** ( 1 minutes  1.268 seconds)
 
 
 .. _sphx_glr_download_how_to_compile_models_from_darknet.py:
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 ce457d55f..60cc298db 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.zip3d4ad8e7-770b-40cf-8e7d-98194e176a32 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+    Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip4f963325-f3ae-4e06-aa8a-0acd95318670 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 f8a85d0f1..a2038f9c4 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -113,7 +113,7 @@ Load a pretrained OneFlow model and save model
  .. code-block:: none
 
     Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
      0%|          | 0.00/41.5M [00:00<?, ?B/s]
     15%|#5        | 6.40M/41.5M [00:00<00:00, 67.1MB/s]
     31%|###       | 12.8M/41.5M [00:00<00:00, 50.4MB/s]
     43%|####3     | 17.8M/41.5M [00:00<00:00, 40.9MB/s]
     58%|#####7    | 24.0M/41.5M [00:00<00:00, 38.4MB/s]
     77%|#######7  | 32.0M/41.5M [00:00<00:00, 45.5MB/s]
     92%|#########2| 38.3M/41.5M [00:00<00:00, 46.5MB/s]
    100%|##########| 41.5M/41.5M [00:00<00:00, 45.9MB/s]
+
      0%|          | 0.00/41.5M [00:00<?, ?B/s]
     19%|#9        | 7.99M/41.5M [00:00<00:00, 45.1MB/s]
     35%|###4      | 14.3M/41.5M [00:00<00:00, 42.6MB/s]
     54%|#####3    | 22.4M/41.5M [00:00<00:00, 55.8MB/s]
     68%|######7   | 28.2M/41.5M [00:00<00:00, 45.3MB/s]
     85%|########4 | 35.2M/41.5M [00:00<00:00, 52.9MB/s]
     98%|#########8| 40.8M/41.5M [00:00<00:00, 52.8MB/s]
    100%|##########| 41.5M/41.5M [00:00<00:00, 51.2MB/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 6b796c76b..99a5c377c 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -94,7 +94,7 @@ Load a pretrained PyTorch model
  .. code-block:: none
 
     Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
-
      0%|          | 0.00/44.7M [00:00<?, ?B/s]
     27%|##7       | 12.2M/44.7M [00:00<00:00, 128MB/s]
     55%|#####4    | 24.5M/44.7M [00:00<00:00, 128MB/s]
    100%|##########| 44.7M/44.7M [00:00<00:00, 157MB/s]
+
      0%|          | 0.00/44.7M [00:00<?, ?B/s]
     40%|###9      | 17.8M/44.7M [00:00<00:00, 186MB/s]
     92%|#########1| 40.9M/44.7M [00:00<00:00, 219MB/s]
    100%|##########| 44.7M/44.7M [00:00<00:00, 217MB/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 7f2f43b68..a276ea722 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -423,7 +423,7 @@ Run the corresponding model on tensorflow
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  1.640 seconds)
+   **Total running time of the script:** ( 1 minutes  0.652 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 17cb6de8d..2c33a2f97 100644
--- a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
 
 Computation times
 =================
-**04:59.280** total execution time for **how_to_compile_models** files:
+**04:54.266** total execution time for **how_to_compile_models** files:
 
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:01.640 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)       | 01:01.268 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)       | 01:01.434 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:00.652 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)         | 00:39.159 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)         | 00:38.297 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)       | 00:28.325 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)       | 00:26.831 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)           | 00:25.406 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)         | 00:24.406 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)         | 00:24.615 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)           | 00:24.192 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)         | 00:21.857 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)         | 00:22.034 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)       | 00:19.681 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)       | 00:19.498 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)           | 00:14.774 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)           | 00:14.765 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)             | 00:02.389 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)             | 00:02.323 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
index dfcef6705..0a6bb157a 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
@@ -441,7 +441,7 @@ Execute on TVM
     Evaluate inference time cost...
     Execution time summary:
      mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)  
-      16.3602      16.3169      17.0110      15.8769       0.3716   
+      14.6335      14.5762      15.0906      14.3597       0.2344   
                
 
 
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 e720a2efc..3caf92f68 100644
--- a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
@@ -123,7 +123,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
  .. code-block:: none
 
     Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
      0%|          | 0.00/170M [00:00<?, ?B/s]
      5%|5         | 8.53M/170M [00:00<00:01, 89.3MB/s]
     13%|#3        | 22.3M/170M [00:00<00:01, 122MB/s] 
     26%|##6       | 44.9M/170M [00:00<00:00, 174MB/s]
     40%|####      | 68.2M/170M [00:00<00:00, 202MB/s]
     54%|#####3    | 91.7M/170M [00:00<00:00, 218MB/s]
     67%|######7   | 114M/170M [00:00<00:00, 224MB/s] 
     82%|########2 | 140M/170M [00:00<00:00, 239MB/s]
     96%|#########5| 163M/170M [00:00<00:00, 240MB/s]
    100%|##########| 170M/170M [00:00<00:00, 216MB/s]
+
      0%|          | 0.00/170M [00:00<?, ?B/s]
      9%|9         | 15.9M/170M [00:00<00:00, 166MB/s]
     19%|#9        | 32.7M/170M [00:00<00:00, 171MB/s]
     30%|###       | 51.1M/170M [00:00<00:00, 181MB/s]
     43%|####3     | 73.6M/170M [00:00<00:00, 201MB/s]
     56%|#####5    | 94.3M/170M [00:00<00:00, 207MB/s]
     68%|######7   | 115M/170M [00:00<00:00, 209MB/s] 
     82%|########2 | 139M/170M [00:00<00:00, 225MB/s]
     96%|#########6| 163M/170M [00:00<00:00, 233MB/s]
    100%|##########| 170M/170M [00:00<00:00, 215MB/s]
     /usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
       for i in range(dim)
     /usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -292,7 +292,7 @@ Get boxes with score larger than 0.9
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 2 minutes  56.936 seconds)
+   **Total running time of the script:** ( 2 minutes  52.291 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 638f0076f..e4f5ebec6 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -232,7 +232,7 @@ training. Other models require a full post training calibration.
  .. code-block:: none
 
     Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
      0%|          | 0.00/13.6M [00:00<?, ?B/s]
    100%|##########| 13.6M/13.6M [00:00<00:00, 183MB/s]
+
      0%|          | 0.00/13.6M [00:00<?, ?B/s]
     21%|##        | 2.84M/13.6M [00:00<00:00, 29.8MB/s]
     48%|####8     | 6.55M/13.6M [00:00<00:00, 35.1MB/s]
    100%|##########| 13.6M/13.6M [00:00<00:00, 60.0MB/s]
 
 
 
@@ -412,7 +412,7 @@ Here we give an example of how to measure performance of TVM compiled models.
 
     Execution time summary:
      mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)  
-      90.2168      90.1767      91.6216      90.0417       0.1971   
+      88.5563      88.5150      91.6298      88.1754       0.3598   
                
 
 
@@ -461,7 +461,7 @@ TODO
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  8.416 seconds)
+   **Total running time of the script:** ( 1 minutes  7.976 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 70f4f5537..1819c4a29 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
@@ -439,7 +439,7 @@ Here we give an example of how to measure performance of TVM compiled models.
 
     Execution time summary:
      mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)  
-      119.8795     119.8115     123.2919     119.0556      0.4566   
+      118.6259     118.6307     121.9512     117.6234      0.4937   
                
 
 
@@ -476,7 +476,7 @@ Here we give an example of how to measure performance of TVM compiled models.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  55.736 seconds)
+   **Total running time of the script:** ( 1 minutes  56.238 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 355e49857..44aaf3084 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -255,7 +255,7 @@ We create a Relay VM to build and execute the model.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  31.595 seconds)
+   **Total running time of the script:** ( 1 minutes  25.594 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 c7c52e784..f5118ea09 100644
--- a/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
@@ -158,7 +158,7 @@ Convert and compile model for CPU.
             data: None
       input_sym_arg_type = in_param.infer_type()[0]
     Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
      0%|          | 0/132723 [00:00<?, ?KB/s]
      4%|4         | 5876/132723 [00:00<00:02, 58755.15KB/s]
     11%|#         | 14224/132723 [00:00<00:01, 73293.49KB/s]
     16%|#6        | 21554/132723 [00:00<00:01, 66847.48KB/s]
     23%|##2       | 30116/132723 [00:00<00:01, 73846.90KB/s]
     29%|##9       | 38702/132723 [00:00<00:01, 78021.68KB/s]
     36%|###5      | 47300/132723 [00:00<00:01, 80660.45KB/s]
     42%|####2     | 55876/132723 [00:00<00:00, 82299.23KB/s]
     49%|####8     | 64424/132723 [00:00<00:00, 83297.50KB/s]
     55%|#####5    | 73065/132723 [00:00<00:00, 84261.62KB/s]
     62%|######1   | 81695/132723 [00:01<00:00, 84885.24KB/s]
     68%|######7   | 90197/132723 [00:01<00:00, 83731.71KB/s]
     74%|#######4  | 98583/132723 [00:01<00:00, 76340.67KB/s]
     81%|########  | 107119/132723 [00:01<00:00, 78873.92KB/s]
     87%|########6 | 115115/132723 [00:01<00:00, 71527.77KB/s]
     93%|#########3| 123700/132723 [00:01<00:00, 75392.18KB/s]
    100%|########
 #9| 132307/132723 [00:01<00:00, 78361.48KB/s]
    100%|##########| 132723/132723 [00:01<00:00, 77934.12KB/s]
+
      0%|          | 0/132723 [00:00<?, ?KB/s]
      4%|4         | 5951/132723 [00:00<00:02, 59505.52KB/s]
     11%|#         | 14482/132723 [00:00<00:01, 74681.89KB/s]
     17%|#6        | 21951/132723 [00:00<00:01, 73710.82KB/s]
     23%|##2       | 30523/132723 [00:00<00:01, 78412.00KB/s]
     29%|##9       | 39113/132723 [00:00<00:01, 81096.28KB/s]
     36%|###5      | 47760/132723 [00:00<00:01, 82912.94KB/s]
     42%|####2     | 56376/132723 [00:00<00:00, 83970.79KB/s]
     49%|####8     | 64985/132723 [00:00<00:00, 84639.90KB/s]
     55%|#####5    | 73564/132723 [00:00<00:00, 84996.59KB/s]
     62%|######1   | 82111/132723 [00:01<00:00, 85137.95KB/s]
     68%|######8   | 90709/132723 [00:01<00:00, 85392.48KB/s]
     75%|#######4  | 99347/132723 [00:01<00:00, 85689.31KB/s]
     81%|########1 | 107935/132723 [00:01<00:00, 85739.78KB/s]
     88%|########7 | 116510/132723 [00:01<00:00, 60780.04KB/s]
     94%|#########4| 125130/132723 [00:01<00:00, 66730.83KB/s]
    100%|########
 ##| 132723/132723 [00:01<00:00, 76760.78KB/s]
 
 
 
@@ -241,7 +241,7 @@ Display result
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 2 minutes  33.784 seconds)
+   **Total running time of the script:** ( 2 minutes  31.487 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 13298708e..375568c2c 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,24 +5,24 @@
 
 Computation times
 =================
-**11:20.023** total execution time for **how_to_deploy_models** files:
+**11:06.648** total execution time for **how_to_deploy_models** files:
 
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 02:56.936 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 02:52.291 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)                           | 02:33.784 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)                           | 02:31.487 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)           | 01:55.736 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)           | 01:56.238 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)                               | 01:31.595 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)                               | 01:25.594 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)                         | 01:08.416 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)                         | 01:07.976 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)                 | 00:29.592 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)                 | 00:28.682 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``)                       | 00:22.186 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``)                       | 00:22.375 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)                       | 00:21.771 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)                       | 00:21.999 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``)                                     | 00:00.006 | 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 8d1dc3145..aab24131f 100644
--- a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
@@ -476,7 +476,7 @@ First let us define two helper functions to get the mobilenet model and a cat im
 
  .. code-block:: none
 
-    Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip011b7b19-964a-432e-b684-65a117c55c10 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+    Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip37540545-1feb-45b6-986d-fc172d475297 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
 
 
 
@@ -590,7 +590,7 @@ Now, to actually convert the entire network, we have written `a pass in Relay <h
 
     /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-      Check failed: (lower) is false: Intrinsic lowering function for target llvm, intrinsic name tir.sqrt, type 150 not found
+      Check failed: (lower) is false: FloatImm lowering function for target llvm type 150 not found
 
 
 
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 5e2d430c2..b7637f3d1 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
@@ -5,12 +5,12 @@
 
 Computation times
 =================
-**00:40.616** total execution time for **how_to_extend_tvm** files:
+**00:40.613** total execution time for **how_to_extend_tvm** files:
 
 +-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:37.483 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:37.459 | 0.0 MB |
 +-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)           | 00:02.195 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)           | 00:02.217 | 0.0 MB |
 +-------------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)                     | 00:00.929 | 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 22b0dde19..c6242fa50 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: 6635us [6635us] (45.62%; 45.62%)
-    FoldScaleAxis: 7911us [6us] (54.38%; 54.38%)
-            FoldConstant: 7904us [1581us] (54.34%; 99.92%)
-                    InferType: 6323us [6323us] (43.47%; 80.00%)
+    InferType: 6423us [6423us] (45.69%; 45.69%)
+    FoldScaleAxis: 7636us [5us] (54.31%; 54.31%)
+            FoldConstant: 7631us [1565us] (54.28%; 99.93%)
+                    InferType: 6066us [6066us] (43.15%; 79.50%)
 
 
 
@@ -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: 6275us [6275us] (44.81%; 44.81%)
-    FoldScaleAxis: 7731us [5us] (55.19%; 55.19%)
-            FoldConstant: 7725us [1613us] (55.16%; 99.93%)
-                    InferType: 6112us [6112us] (43.64%; 79.12%)
+    InferType: 6142us [6142us] (44.24%; 44.24%)
+    FoldScaleAxis: 7740us [6us] (55.76%; 55.76%)
+            FoldConstant: 7734us [1628us] (55.71%; 99.92%)
+                    InferType: 6105us [6105us] (43.98%; 78.94%)
 
 
 
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 e14f8c82e..88a9abfa8 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: 54.143435 ms
+    Convolution: 54.282266 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 c3d906b90..7898637ff 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
@@ -671,7 +671,7 @@ be able to run on our build server
 
  .. code-block:: none
 
-    conv2d with tensor core: 6.874169 ms
+    conv2d with tensor core: 8.974075 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 60fee7bb3..95b4a8ae9 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: 0.018770
-    Baseline: 3.443516
+    Numpy running time: 0.016981
+    Baseline: 3.275948
 
 
 
@@ -239,7 +239,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
 
  .. code-block:: none
 
-    Opt1: 0.297884
+    Opt1: 0.296299
 
 
 
@@ -342,7 +342,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
 
  .. code-block:: none
 
-    Opt2: 0.332118
+    Opt2: 0.334851
 
 
 
@@ -438,7 +438,7 @@ the access pattern for A matrix is more cache friendly.
 
  .. code-block:: none
 
-    Opt3: 0.115934
+    Opt3: 0.113997
 
 
 
@@ -563,7 +563,7 @@ flattening.
 
  .. code-block:: none
 
-    Opt4: 0.110889
+    Opt4: 0.109449
 
 
 
@@ -685,7 +685,7 @@ write to C when all the block results are ready.
 
  .. code-block:: none
 
-    Opt5: 0.111615
+    Opt5: 0.103335
 
 
 
@@ -810,7 +810,7 @@ Futhermore, we can also utilize multi-core processors to do the thread-level par
 
  .. code-block:: none
 
-    Opt6: 0.144957
+    Opt6: 0.133752
 
 
 
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 0f8a524b3..b1261b55b 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
 
 Computation times
 =================
-**00:34.478** total execution time for **how_to_optimize_operators** files:
+**00:32.980** total execution time for **how_to_optimize_operators** files:
 
 +-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)                       | 00:32.219 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)                       | 00:30.819 | 0.0 MB |
 +-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.231 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.201 | 0.0 MB |
 +-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)             | 00:01.029 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)             | 00:00.960 | 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 10c0f72e1..1a84bcc9e 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
 =================
-**06:05.157** total execution time for **how_to_tune_with_autoscheduler** files:
+**06:04.566** total execution time for **how_to_tune_with_autoscheduler** files:
 
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 03:19.557 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 03:14.676 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)             | 01:22.001 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)             | 01:22.732 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)           | 00:46.087 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)           | 00:46.180 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)               | 00:20.142 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)               | 00:23.425 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)           | 00:08.758 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)           | 00:08.883 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)             | 00:08.611 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)             | 00:08.670 | 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 05a5a0d0a..4c500cbe8 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
@@ -240,413 +240,76 @@ cooperative fetching, unrolling and operator fusion.
                  compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
       buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
       preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
-      attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 32;
-      allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
-      allocate(pad_temp.shared: Pointer(shared float32), float32, [504]), storage_scope = shared;
-      allocate(kernel.shared: Pointer(shared float32), float32, [384]), storage_scope = shared;
+      attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 112;
+      allocate(conv2d_nchw: Pointer(local float32), float32, [4]), storage_scope = local;
+      allocate(pad_temp.shared: Pointer(shared float32), float32, [54]), storage_scope = shared;
+      allocate(kernel.shared: Pointer(shared float32), float32, [576]), storage_scope = shared;
       attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
-        conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=8)[0] = 0f32
-        conv2d_nchw_1[2] = 0f32
-        conv2d_nchw_1[4] = 0f32
-        conv2d_nchw_1[6] = 0f32
-        conv2d_nchw_1[8] = 0f32
-        conv2d_nchw_1[10] = 0f32
-        conv2d_nchw_1[12] = 0f32
+        conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=16)[0] = 0f32
         conv2d_nchw_1[1] = 0f32
+        conv2d_nchw_1[2] = 0f32
         conv2d_nchw_1[3] = 0f32
-        conv2d_nchw_1[5] = 0f32
-        conv2d_nchw_1[7] = 0f32
-        conv2d_nchw_1[9] = 0f32
-        conv2d_nchw_1[11] = 0f32
-        conv2d_nchw_1[13] = 0f32
-        for (rc.outer.outer: int32, 0, 64) {
-          for (ry.outer.outer: int32, 0, 3) {
-            let cse_var_4: int32 = (rc.outer.outer*392)
-            let cse_var_3: int32 = (ry.outer.outer*7)
-            let cse_var_2: int32 = (rc.outer.outer*72)
-            let cse_var_1: int32 = (ry.outer.outer*3)
-             {
-              attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
-              pad_temp.shared_1: Buffer(pad_temp.shared, float32, [504], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && ((floordiv(threadIdx.x_1, 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
-              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
-              pad_temp.shared_1[(threadIdx.x_1 + 56)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 56), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
-              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
-              pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 112), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
-              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
-              pad_temp.shared_1[(threadIdx.x_1 + 168)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 168), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
-              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
-              pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 224), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
-              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
-              pad_temp.shared_1[(threadIdx.x_1 + 280)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 280), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
-              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
-              pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 336), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
-              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
-              pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 392), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
-              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
-              pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 448), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
-              attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
-              kernel.shared_1: Buffer(kernel.shared, float32, [384], [], scope="shared")[threadIdx.x_2] = kernel[((((((blockIdx.x*73728) + (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" = 56;
-              kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 56), 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" = 56;
-              kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 112), 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" = 56;
-              kernel.shared_1[(threadIdx.x_2 + 168)] = kernel[(((((((blockIdx.x*73728) + (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)) + 32256)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
-              kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 224), 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" = 56;
-              kernel.shared_1[(threadIdx.x_2 + 280)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 280), 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" = 56;
-              if @tir.likely((threadIdx.x_2 < 48), dtype=bool) {
-                kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[(((((((blockIdx.x*73728) + (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)) + 64512)]
-              }
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*9)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*48)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*48)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*48)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*48)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*48)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*48)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*48)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 24)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 24)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 24)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 24)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 24)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 24)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 24)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 1)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 1)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 1)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 1)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 1)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 1)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 1)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 25)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 25)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 25)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 25)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 25)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 25)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 25)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 2)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 2)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 2)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 2)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 2)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 2)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 8)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 2)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 26)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 26)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 26)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 26)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 26)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 26)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 8)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 26)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 3)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 3)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 3)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 66)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 3)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 67)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 3)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 68)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 3)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 69)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 3)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 27)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 27)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 27)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 66)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 27)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 67)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 27)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 68)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 27)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 69)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 27)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 4)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 4)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 66)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 4)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 67)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 4)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 68)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 4)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 69)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 4)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 70)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 4)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 28)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 28)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 66)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 28)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 67)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 28)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 68)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 28)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 69)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 28)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 70)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 28)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 5)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 66)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 5)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 67)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 5)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 68)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 5)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 69)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 5)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 70)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 5)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 71)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 5)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 29)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 66)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 29)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 67)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 29)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 68)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 29)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 69)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 29)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 70)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 29)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 71)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 29)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 6)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 6)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 6)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 129)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 6)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 130)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 6)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 131)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 6)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 132)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 6)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 30)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 30)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 30)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 129)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 30)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 130)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 30)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 131)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 30)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 132)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 30)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 7)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 7)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 129)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 7)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 130)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 7)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 131)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 7)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 132)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 7)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 133)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 7)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 31)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 31)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 129)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 31)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 130)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 31)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 131)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 31)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 132)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 31)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 133)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 31)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 8)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 129)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 8)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 130)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 8)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 131)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 8)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 132)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 8)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 133)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 8)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 134)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 8)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 32)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 129)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 32)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 130)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 32)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 131)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 32)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 132)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 32)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 133)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 32)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 134)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 32)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 9)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 9)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 9)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 192)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 9)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 193)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 9)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 194)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 9)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 195)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 9)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 33)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 33)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 33)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 192)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 33)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 193)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 33)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 194)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 33)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 195)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 33)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 10)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 10)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 192)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 10)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 193)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 10)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 194)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 10)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 195)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 10)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 10)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 34)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 34)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 192)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 34)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 193)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 34)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 194)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 34)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 195)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 34)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 34)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 11)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 192)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 11)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 193)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 11)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 194)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 11)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 195)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 11)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 11)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 11)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 35)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 192)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 35)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 193)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 35)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 194)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 35)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 195)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 35)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 35)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 35)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 12)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 12)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 12)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 12)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 12)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 12)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 12)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 36)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 36)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 36)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 36)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 36)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 36)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 36)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 13)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 13)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 13)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 13)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 13)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 13)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 13)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 37)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 37)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 37)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 37)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 37)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 37)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 37)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 14)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 14)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 14)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 14)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 14)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 14)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 260)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 14)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 38)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 38)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 38)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 38)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 38)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 38)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 260)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 38)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 315)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 15)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 15)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 15)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 318)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 15)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 319)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 15)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 320)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 15)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 321)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 15)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 315)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 39)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 39)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 39)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 318)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 39)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 319)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 39)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 320)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 39)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 321)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 39)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 16)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 16)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 318)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 16)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 319)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 16)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 320)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 16)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 321)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 16)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 322)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 16)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 40)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 40)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 318)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 40)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 319)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 40)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 320)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 40)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 321)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 40)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 322)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 40)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 17)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 318)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 17)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 319)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 17)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 320)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 17)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 321)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 17)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 322)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 17)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 323)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 17)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 41)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 318)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 41)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 319)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 41)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 320)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 41)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 321)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 41)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 322)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 41)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 323)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 41)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 18)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 18)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 18)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 381)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 18)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 382)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 18)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 383)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 18)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 384)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 18)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 42)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 42)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 42)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 381)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 42)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 382)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 42)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 383)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 42)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 384)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 42)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 19)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 19)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 381)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 19)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 382)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 19)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 383)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 19)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 384)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 19)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 385)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 19)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 43)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 43)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 381)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 43)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 382)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 43)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 383)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 43)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 384)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 43)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 385)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 43)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 20)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 381)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 20)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 382)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 20)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 383)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 20)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 384)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 20)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 385)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 20)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 386)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 20)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 44)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 381)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 44)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 382)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 44)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 383)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 44)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 384)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 44)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 385)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 44)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 386)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 44)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 21)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 21)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 21)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 444)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 21)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 445)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 21)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 446)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 21)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 447)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 21)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 45)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 45)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 45)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 444)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 45)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 445)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 45)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 446)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 45)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 447)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 45)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 22)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 22)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 444)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 22)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 445)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 22)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 446)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 22)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 447)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 22)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 448)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 22)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 46)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 46)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 444)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 46)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 445)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 46)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 446)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 46)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 447)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 46)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 448)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 46)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 23)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 444)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 23)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 445)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 23)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 446)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 23)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 447)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 23)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 448)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 23)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 449)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 23)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 47)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 444)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 47)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 445)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 47)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 446)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 47)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 447)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 47)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 448)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 47)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 449)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 47)]))
+        for (rc.outer.outer: int32, 0, 256) {
+          let cse_var_1: int32 = (rc.outer.outer*18)
+           {
+            attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+            if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+              pad_temp.shared_1: Buffer(pad_temp.shared, float32, [54], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((1 <= (floordiv(floormod(threadIdx.x_1, 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod(threadIdx.x_1, 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((((rc.outer.outer*98) + (floordiv(threadIdx.x_1, 27)*49)) + (floordiv(floormod(threadIdx.x_1, 27), 9)*7)) + (floormod(block [...]
+            }
+            attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+            kernel.shared_1: Buffer(kernel.shared, float32, [576], [], scope="shared")[threadIdx.x_2] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 18))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+            kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 56), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 18))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+            kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 112), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 18))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+            kernel.shared_1[(threadIdx.x_2 + 168)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 168), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 6), 18))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+            kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 224), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 18))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+            kernel.shared_1[(threadIdx.x_2 + 280)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 280), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 10), 18))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+            kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 336), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 12), 18))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+            kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 392), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 14), 18))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+            kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 448), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 18))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+            kernel.shared_1[(threadIdx.x_2 + 504)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 18)) + 129024)]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+            if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+              kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 560), 18)*4608)) + cse_var_1) + (threadIdx.x_2 + 2))]
+            }
+            for (rx.outer.inner: int32, 0, 3) {
+              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(rx.outer.inner + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + rx.outer.inner)]))
+              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(rx.outer.inner + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 18)]))
+              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(rx.outer.inner + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 36)]))
+              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(rx.outer.inner + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 54)]))
+              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 3)]))
+              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 21)]))
+              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 39)]))
+              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 57)]))
+              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 6)]))
+              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 24)]))
+              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 42)]))
+              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 60)]))
+              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 9)]))
+              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 27)]))
+              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 45)]))
+              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 63)]))
+              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 12)]))
+              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 30)]))
+              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 48)]))
+              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 66)]))
+              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 15)]))
+              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 33)]))
+              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 51)]))
+              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 69)]))
             }
           }
         }
-        for (i1.inner: int32, 0, 2) {
-          compute[((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
-          compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 1)] = max((conv2d_nchw_1[(i1.inner + 2)] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
-          compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 2)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
-          compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 3)] = max((conv2d_nchw_1[(i1.inner + 6)] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
-          compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 4)] = max((conv2d_nchw_1[(i1.inner + 8)] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
-          compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 5)] = max((conv2d_nchw_1[(i1.inner + 10)] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
-          compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 6)] = max((conv2d_nchw_1[(i1.inner + 12)] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+        for (i1.inner: int32, 0, 4) {
+          compute[(((((floordiv(blockIdx.x, 7)*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[i1.inner] + bias[(((floordiv(blockIdx.x, 7)*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
         }
       }
     }
@@ -701,7 +364,7 @@ We build the binary and check its correctness and performance.
 
  .. code-block:: none
 
-    Execution time of this operator: 0.221 ms
+    Execution time of this operator: 0.391 ms
 
 
 
@@ -749,37 +412,37 @@ 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=2)
+    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=7)
+    conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
     conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
     conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
     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=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_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
+    conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
+    conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
+    conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
+    conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
     conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
-    conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
-    conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
+    conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
+    conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
     s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
     compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
     compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
     compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
-    compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
+    compute_i1_o_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=7)
+    compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
     compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
     compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=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=7)
+    compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
+    compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
     s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
     s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
     kernel_shared = s.cache_read(kernel, "shared", [conv2d_nchw])
@@ -805,7 +468,7 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
     s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
     pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
     s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
-    s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
+    s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 64)
     s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
 
     CUDA source code:
@@ -824,391 +487,61 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
       #define uint64_t unsigned long long
     #endif
     extern "C" __global__ void __launch_bounds__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
-      float conv2d_nchw[14];
-      __shared__ float pad_temp_shared[504];
-      __shared__ float kernel_shared[384];
+      float conv2d_nchw[4];
+      __shared__ float pad_temp_shared[54];
+      __shared__ float kernel_shared[576];
       conv2d_nchw[0] = 0.000000e+00f;
-      conv2d_nchw[2] = 0.000000e+00f;
-      conv2d_nchw[4] = 0.000000e+00f;
-      conv2d_nchw[6] = 0.000000e+00f;
-      conv2d_nchw[8] = 0.000000e+00f;
-      conv2d_nchw[10] = 0.000000e+00f;
-      conv2d_nchw[12] = 0.000000e+00f;
       conv2d_nchw[1] = 0.000000e+00f;
+      conv2d_nchw[2] = 0.000000e+00f;
       conv2d_nchw[3] = 0.000000e+00f;
-      conv2d_nchw[5] = 0.000000e+00f;
-      conv2d_nchw[7] = 0.000000e+00f;
-      conv2d_nchw[9] = 0.000000e+00f;
-      conv2d_nchw[11] = 0.000000e+00f;
-      conv2d_nchw[13] = 0.000000e+00f;
-      for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
-        for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
-          __syncthreads();
-          pad_temp_shared[((int)threadIdx.x)] = (((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (((((int)threadIdx.x) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
-          pad_temp_shared[(((int)threadIdx.x) + 56)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 56) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
-          pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 112) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
-          pad_temp_shared[(((int)threadIdx.x) + 168)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 168) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
-          pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
-          pad_temp_shared[(((int)threadIdx.x) + 280)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 280) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
-          pad_temp_shared[(((int)threadIdx.x) + 336)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 336) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
-          pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 392) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
-          pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((1 <= (((((int)threadIdx.x) + 7) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) + 7) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 448) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
-          kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((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) + 56)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) / 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) + 112)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 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) + 168)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 32256)];
-          kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 224) / 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) + 280)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          if (((int)threadIdx.x) < 48) {
-            kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 64512)];
-          }
-          __syncthreads();
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 9)] * kernel_shared[((((int)threadIdx.x) / 7) * 48)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[((((int)threadIdx.x) / 7) * 48)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[((((int)threadIdx.x) / 7) * 48)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[((((int)threadIdx.x) / 7) * 48)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[((((int)threadIdx.x) / 7) * 48)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[((((int)threadIdx.x) / 7) * 48)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[((((int)threadIdx.x) / 7) * 48)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 24)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 24)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 24)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 24)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 24)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 24)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 24)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 1)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 1)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 1)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 1)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 1)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 1)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 1)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 25)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 25)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 25)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 25)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 25)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 25)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 25)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 2)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 2)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 2)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 2)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 2)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 2)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 8)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 2)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 26)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 26)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 26)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 26)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 26)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 26)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 8)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 26)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 3)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 3)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 3)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 66)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 3)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 67)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 3)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 68)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 3)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 69)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 3)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 27)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 27)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 27)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 66)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 27)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 67)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 27)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 68)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 27)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 69)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 27)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 4)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 4)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 66)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 4)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 67)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 4)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 68)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 4)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 69)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 4)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 70)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 4)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 28)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 28)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 66)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 28)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 67)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 28)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 68)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 28)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 69)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 28)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 70)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 28)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 5)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 66)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 5)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 67)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 5)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 68)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 5)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 69)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 5)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 70)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 5)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 71)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 5)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 29)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 66)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 29)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 67)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 29)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 68)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 29)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 69)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 29)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 70)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 29)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 71)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 29)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 6)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 6)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 6)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 129)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 6)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 130)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 6)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 131)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 6)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 132)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 6)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 30)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 30)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 30)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 129)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 30)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 130)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 30)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 131)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 30)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 132)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 30)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 7)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 7)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 129)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 7)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 130)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 7)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 131)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 7)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 132)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 7)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 133)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 7)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 31)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 31)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 129)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 31)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 130)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 31)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 131)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 31)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 132)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 31)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 133)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 31)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 8)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 129)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 8)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 130)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 8)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 131)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 8)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 132)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 8)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 133)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 8)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 134)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 8)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 32)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 129)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 32)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 130)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 32)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 131)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 32)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 132)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 32)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 133)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 32)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 134)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 32)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 9)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 9)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 9)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 192)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 9)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 193)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 9)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 194)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 9)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 195)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 9)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 33)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 33)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 33)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 192)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 33)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 193)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 33)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 194)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 33)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 195)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 33)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 10)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 10)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 192)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 10)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 193)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 10)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 194)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 10)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 195)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 10)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 10)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 34)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 34)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 192)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 34)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 193)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 34)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 194)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 34)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 195)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 34)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 34)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 11)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 192)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 11)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 193)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 11)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 194)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 11)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 195)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 11)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 11)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 11)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 35)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 192)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 35)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 193)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 35)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 194)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 35)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 195)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 35)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 35)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 35)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 12)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 12)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 12)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 12)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 12)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 12)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 12)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 36)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 36)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 36)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 36)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 36)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 36)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 36)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 13)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 13)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 13)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 13)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 13)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 13)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 13)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 37)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 37)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 37)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 37)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 37)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 37)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 37)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 14)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 14)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 14)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 14)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 14)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 14)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 260)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 14)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 38)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 38)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 38)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 38)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 38)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 38)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 260)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 38)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 315)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 15)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 15)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 15)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 318)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 15)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 319)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 15)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 320)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 15)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 321)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 15)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 315)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 39)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 39)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 39)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 318)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 39)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 319)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 39)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 320)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 39)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 321)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 39)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 16)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 16)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 318)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 16)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 319)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 16)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 320)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 16)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 321)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 16)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 322)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 16)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 40)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 40)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 318)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 40)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 319)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 40)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 320)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 40)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 321)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 40)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 322)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 40)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 17)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 318)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 17)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 319)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 17)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 320)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 17)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 321)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 17)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 322)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 17)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 323)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 17)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 41)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 318)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 41)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 319)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 41)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 320)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 41)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 321)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 41)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 322)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 41)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 323)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 41)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 378)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 18)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 18)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 18)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 381)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 18)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 382)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 18)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 383)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 18)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 384)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 18)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 378)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 42)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 42)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 42)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 381)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 42)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 382)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 42)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 383)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 42)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 384)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 42)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 19)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 19)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 381)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 19)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 382)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 19)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 383)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 19)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 384)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 19)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 385)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 19)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 43)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 43)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 381)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 43)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 382)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 43)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 383)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 43)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 384)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 43)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 385)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 43)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 20)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 381)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 20)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 382)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 20)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 383)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 20)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 384)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 20)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 385)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 20)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 386)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 20)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 44)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 381)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 44)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 382)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 44)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 383)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 44)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 384)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 44)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 385)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 44)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 386)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 44)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 441)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 21)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 21)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 21)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 444)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 21)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 445)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 21)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 446)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 21)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 447)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 21)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 441)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 45)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 45)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 45)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 444)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 45)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 445)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 45)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 446)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 45)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 447)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 45)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 22)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 22)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 444)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 22)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 445)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 22)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 446)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 22)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 447)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 22)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 448)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 22)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 46)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 46)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 444)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 46)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 445)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 46)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 446)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 46)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 447)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 46)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 448)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 46)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 23)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 444)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 23)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 445)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 23)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 446)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 23)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 447)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 23)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 448)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 23)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 449)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 23)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 47)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 444)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 47)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 445)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 47)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 446)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 47)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 447)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 47)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 448)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 47)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 449)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 47)]));
+      for (int rc_outer_outer = 0; rc_outer_outer < 256; ++rc_outer_outer) {
+        __syncthreads();
+        if (((int)threadIdx.x) < 54) {
+          pad_temp_shared[((int)threadIdx.x)] = (((((1 <= (((((int)threadIdx.x) % 27) / 9) + (((int)blockIdx.x) % 7))) && ((((((int)threadIdx.x) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((((rc_outer_outer * 98) + ((((int)threadIdx.x) / 27) * 49)) + (((((int)threadIdx.x) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+        }
+        kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 18)) + (((int)threadIdx.x) % 18))];
+        kernel_shared[(((int)threadIdx.x) + 56)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 56) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 2) % 18))];
+        kernel_shared[(((int)threadIdx.x) + 112)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 4) % 18))];
+        kernel_shared[(((int)threadIdx.x) + 168)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 168) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 6) % 18))];
+        kernel_shared[(((int)threadIdx.x) + 224)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 8) % 18))];
+        kernel_shared[(((int)threadIdx.x) + 280)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 280) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 10) % 18))];
+        kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 336) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 12) % 18))];
+        kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 392) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 14) % 18))];
+        kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 16) % 18))];
+        kernel_shared[(((int)threadIdx.x) + 504)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 18)) + (((int)threadIdx.x) % 18)) + 129024)];
+        if (((int)threadIdx.x) < 16) {
+          kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 560) / 18) * 4608)) + (rc_outer_outer * 18)) + ((int)threadIdx.x)) + 2)];
+        }
+        __syncthreads();
+        for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
+          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(rx_outer_inner + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + rx_outer_inner)]));
+          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(rx_outer_inner + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 18)]));
+          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(rx_outer_inner + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 36)]));
+          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(rx_outer_inner + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 54)]));
+          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 3)]));
+          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 21)]));
+          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 39)]));
+          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 57)]));
+          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 6)]));
+          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 24)]));
+          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 42)]));
+          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 60)]));
+          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 9)]));
+          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 27)]));
+          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 45)]));
+          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 63)]));
+          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 12)]));
+          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 30)]));
+          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 48)]));
+          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 66)]));
+          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 15)]));
+          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 33)]));
+          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 51)]));
+          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 69)]));
         }
       }
-      for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
-        compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
-        compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 1)] = max((conv2d_nchw[(i1_inner + 2)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
-        compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 2)] = max((conv2d_nchw[(i1_inner + 4)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
-        compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 3)] = max((conv2d_nchw[(i1_inner + 6)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
-        compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 4)] = max((conv2d_nchw[(i1_inner + 8)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
-        compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 5)] = max((conv2d_nchw[(i1_inner + 10)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
-        compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 6)] = max((conv2d_nchw[(i1_inner + 12)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+      for (int i1_inner = 0; i1_inner < 4; ++i1_inner) {
+        compute[((((((((int)blockIdx.x) / 7) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i1_inner] + bias[((((((int)blockIdx.x) / 7) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
       }
     }
 
@@ -1270,7 +603,7 @@ In the example below we resume the status and do more 5 trials.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 3 minutes  19.557 seconds)
+   **Total running time of the script:** ( 3 minutes  14.676 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 725b317be..45aeb5f0d 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -647,7 +647,7 @@ so we can read the log file and load the best schedules.
     Evaluate inference time cost...
     Execution time summary:
      mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)  
-       9.7572       9.7757       9.8059       9.6899       0.0492   
+      10.0790      10.1018      10.1067      10.0283       0.0359   
                
 
 
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 058425337..7b07351a1 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
@@ -666,7 +666,7 @@ so we can read the log file and load the best schedules.
     Evaluate inference time cost...
     Execution time summary:
      mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)  
-      760.1820     760.4577     760.7874     759.3009      0.6374   
+      753.3373     753.6253     753.7449     752.6417      0.4943   
                
 
 
@@ -694,7 +694,7 @@ Other Tips
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  22.001 seconds)
+   **Total running time of the script:** ( 1 minutes  22.732 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 4ef431df8..25e4a0c08 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
@@ -397,31 +397,103 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
                  placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
                  compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
       buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
-      preflattened_buffer_map = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_8: placeholder_15: Buffer(placeholder_13, int32, [33], []), placeholder_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_5: placeholder_17: Buffer(placeholder_10, float32, [128, 256], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], [])} {
+      preflattened_buffer_map = {placeholder_8: placeholder_15: Buffer(placeholder_13, int32, [33], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
       for (i0.outer.i1.outer.fused: int32, 0, 32) "parallel" {
         allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global {
-          for (i.outer.inner: int32, 0, 32) {
-            for (i.inner.init: int32, 0, 4) {
-              for (j.init: int32, 0, 16) {
-                compute_5: Buffer(compute_4, float32, [2048], [])[(((i.outer.inner*64) + (i.inner.init*16)) + j.init)] = 0f32
+          for (i.outer.inner: int32, 0, 4) {
+            for (i.inner.init: int32, 0, 32) {
+              let cse_var_1: int32 = ((i.outer.inner*512) + (i.inner.init*16))
+               {
+                compute_5: Buffer(compute_4, float32, [2048], [])[cse_var_1] = 0f32
+                compute_5[(cse_var_1 + 1)] = 0f32
+                compute_5[(cse_var_1 + 2)] = 0f32
+                compute_5[(cse_var_1 + 3)] = 0f32
+                compute_5[(cse_var_1 + 4)] = 0f32
+                compute_5[(cse_var_1 + 5)] = 0f32
+                compute_5[(cse_var_1 + 6)] = 0f32
+                compute_5[(cse_var_1 + 7)] = 0f32
+                compute_5[(cse_var_1 + 8)] = 0f32
+                compute_5[(cse_var_1 + 9)] = 0f32
+                compute_5[(cse_var_1 + 10)] = 0f32
+                compute_5[(cse_var_1 + 11)] = 0f32
+                compute_5[(cse_var_1 + 12)] = 0f32
+                compute_5[(cse_var_1 + 13)] = 0f32
+                compute_5[(cse_var_1 + 14)] = 0f32
+                compute_5[(cse_var_1 + 15)] = 0f32
               }
             }
             for (elem_idx: int32, 0, (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])) {
-              for (i.inner: int32, 0, 4) {
-                for (j: int32, 0, 16) {
-                  if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
-                    let cse_var_1: int32 = (((i.outer.inner*64) + (i.inner*16)) + j)
-                    compute_5[cse_var_1] = (compute_5[cse_var_1] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + j)]*max(placeholder[(((i.outer.inner*1024) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
-                  }
+              for (i.inner: int32, 0, 32) {
+                if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+                  let cse_var_2: int32 = ((i.outer.inner*512) + (i.inner*16))
+                  compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16))]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+                }
+                if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+                  let cse_var_3: int32 = (((i.outer.inner*512) + (i.inner*16)) + 1)
+                  compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+                }
+                if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+                  let cse_var_4: int32 = (((i.outer.inner*512) + (i.inner*16)) + 2)
+                  compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+                }
+                if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+                  let cse_var_5: int32 = (((i.outer.inner*512) + (i.inner*16)) + 3)
+                  compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+                }
+                if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+                  let cse_var_6: int32 = (((i.outer.inner*512) + (i.inner*16)) + 4)
+                  compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+                }
+                if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+                  let cse_var_7: int32 = (((i.outer.inner*512) + (i.inner*16)) + 5)
+                  compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+                }
+                if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+                  let cse_var_8: int32 = (((i.outer.inner*512) + (i.inner*16)) + 6)
+                  compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+                }
+                if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+                  let cse_var_9: int32 = (((i.outer.inner*512) + (i.inner*16)) + 7)
+                  compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+                }
+                if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+                  let cse_var_10: int32 = (((i.outer.inner*512) + (i.inner*16)) + 8)
+                  compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+                }
+                if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+                  let cse_var_11: int32 = (((i.outer.inner*512) + (i.inner*16)) + 9)
+                  compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+                }
+                if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+                  let cse_var_12: int32 = (((i.outer.inner*512) + (i.inner*16)) + 10)
+                  compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+                }
+                if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+                  let cse_var_13: int32 = (((i.outer.inner*512) + (i.inner*16)) + 11)
+                  compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+                }
+                if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+                  let cse_var_14: int32 = (((i.outer.inner*512) + (i.inner*16)) + 12)
+                  compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+                }
+                if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+                  let cse_var_15: int32 = (((i.outer.inner*512) + (i.inner*16)) + 13)
+                  compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+                }
+                if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+                  let cse_var_16: int32 = (((i.outer.inner*512) + (i.inner*16)) + 14)
+                  compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+                }
+                if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+                  let cse_var_17: int32 = (((i.outer.inner*512) + (i.inner*16)) + 15)
+                  compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
                 }
               }
             }
           }
           for (i0.inner: int32, 0, 128) {
-            for (i1.inner: int32, 0, 16) {
-              let cse_var_2: int32 = (((i0.inner*512) + (i0.outer.i1.outer.fused*16)) + i1.inner)
-              compute[cse_var_2] = max((compute_5[((i0.inner*16) + i1.inner)] + placeholder_4[cse_var_2]), 0f32)
-            }
+            let cse_var_18: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*16))
+            compute[ramp(cse_var_18, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_18, 1, 16)]), broadcast(0f32, 16))
           }
         }
       }
@@ -477,7 +549,7 @@ We build the binary and check its correctness and performance.
 
  .. code-block:: none
 
-    Execution time of this operator: 1.462 ms
+    Execution time of this operator: 1.790 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 5e5a4651a..44debc0e6 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
 
 Computation times
 =================
-**00:45.293** total execution time for **how_to_tune_with_autotvm** files:
+**00:45.147** total execution time for **how_to_tune_with_autotvm** files:
 
 +--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)           | 00:45.258 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)           | 00:45.110 | 0.0 MB |
 +--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)               | 00:00.020 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)               | 00:00.023 | 0.0 MB |
 +--------------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``)             | 00:00.005 | 0.0 MB |
 +--------------------------------------------------------------------------------------------------+-----------+--------+
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 cc3d65b8b..9698ed032 100644
--- a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
@@ -1156,8 +1156,8 @@ for this template
     TimeoutError
 
             [('tile_f', [-1, 2, 1, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4909501
-    No: 9   GFLOPS: 181.47/181.47   result: MeasureResult(costs=(0.001275734888888889,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0310184955596924, timestamp=1659640918.6263578)       [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
-    No: 10  GFLOPS: 0.00/181.47     result: Traceback (most recent call last):
+    No: 9   GFLOPS: 219.59/219.59   result: MeasureResult(costs=(0.0010542364275862067,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1123545169830322, timestamp=1659647699.6992056)      [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
+    No: 10  GFLOPS: 0.00/219.59     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1280,8 +1280,8 @@ for this template
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
     tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 4, 4, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5092711
-    No: 11  GFLOPS: 261.10/261.10   result: MeasureResult(costs=(0.000886633017699115,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.445702075958252, timestamp=1659640919.2690825)        [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
-    No: 12  GFLOPS: 0.00/261.10     result: Traceback (most recent call last):
+    No: 11  GFLOPS: 260.07/260.07   result: MeasureResult(costs=(0.0008901485635359116,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7547366619110107, timestamp=1659647700.6220863)      [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
+    No: 12  GFLOPS: 0.00/260.07     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1404,7 +1404,7 @@ for this template
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
     tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 128, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,183542
-    No: 13  GFLOPS: 0.00/261.10     result: Traceback (most recent call last):
+    No: 13  GFLOPS: 0.00/260.07     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1527,7 +1527,7 @@ for this template
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
     tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 4, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2482196
-    No: 14  GFLOPS: 0.00/261.10     result: Traceback (most recent call last):
+    No: 14  GFLOPS: 0.00/260.07     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1650,9 +1650,9 @@ for this template
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
     tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 64, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10306226
-    No: 15  GFLOPS: 5.32/261.10     result: MeasureResult(costs=(0.043493526250000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8619730472564697, timestamp=1659640923.8461597)       [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
-    No: 16  GFLOPS: 3.35/261.10     result: MeasureResult(costs=(0.0691233745,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.541823625564575, timestamp=1659640925.0787606)        [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
-    No: 17  GFLOPS: 0.00/261.10     result: Traceback (most recent call last):
+    No: 15  GFLOPS: 5.29/260.07     result: MeasureResult(costs=(0.043795402250000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.839280366897583, timestamp=1659647705.1306255)        [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
+    No: 16  GFLOPS: 3.34/260.07     result: MeasureResult(costs=(0.06939814200000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.486169099807739, timestamp=1659647706.3674533) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
+    No: 17  GFLOPS: 0.00/260.07     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
         res = future.result()
       File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
@@ -1670,8 +1670,8 @@ for this template
     TimeoutError
 
             [('tile_f', [-1, 2, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10195251
-    No: 18  GFLOPS: 28.12/261.10    result: MeasureResult(costs=(0.008231936142857143,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3359155654907227, timestamp=1659640936.1278422)       [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
-    No: 19  GFLOPS: 0.00/261.10     result: Traceback (most recent call last):
+    No: 18  GFLOPS: 28.05/260.07    result: MeasureResult(costs=(0.008254217285714285,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.293917179107666, timestamp=1659647717.3834984)        [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
+    No: 19  GFLOPS: 0.00/260.07     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1794,7 +1794,7 @@ for this template
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
     tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6956993
-    No: 20  GFLOPS: 0.00/261.10     result: Traceback (most recent call last):
+    No: 20  GFLOPS: 0.00/260.07     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1973,7 +1973,7 @@ and measure running time.
     Best config:
     [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
     Finish loading 20 records
-    Time cost of this operator: 0.001262
+    Time cost of this operator: 0.001240
 
 
 
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 3941a7cc0..b44572fd0 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  311.1     98.732   (1, 2, 10, 10, 3)  2       1        [311.1]           
-    tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       3.015     0.957    (1, 6, 10, 10)     1       1        [3.015]           
-    tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.979     0.311    (1, 1, 10, 10, 3)  1       1        [0.979]           
-    Total_time                                    -                                             315.094   -        -                  -       -        -                 
+    tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  318.1     98.76    (1, 2, 10, 10, 3)  2       1        [318.1]           
+    tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       3.03      0.941    (1, 6, 10, 10)     1       1        [3.03]            
+    tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.965     0.3      (1, 1, 10, 10, 3)  1       1        [0.965]           
+    Total_time                                    -                                             322.095   -        -                  -       -        -                 
 
 
 
@@ -398,10 +398,10 @@ Timing the tuned program
     ########## Build with Autotuning ##########
     Node Name                                     Ops                                           Time(us)  Time(%)  Shape              Inputs  Outputs  Measurements(us)  
     ---------                                     ---                                           --------  -------  -----              ------  -------  ----------------  
-    tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  93.438    97.252   (1, 6, 10, 10, 1)  2       1        [93.438]          
-    tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       1.777     1.85     (1, 6, 10, 10)     1       1        [1.777]           
-    tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.863     0.899    (1, 3, 10, 10, 1)  1       1        [0.863]           
-    Total_time                                    -                                             96.078    -        -                  -       -        -                 
+    tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  195.6     98.675   (1, 6, 10, 10, 1)  2       1        [195.6]           
+    tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       1.784     0.9      (1, 6, 10, 10)     1       1        [1.784]           
+    tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.842     0.425    (1, 3, 10, 10, 1)  1       1        [0.842]           
+    Total_time                                    -                                             198.226   -        -                  -       -        -                 
 
 
 
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 3874809c5..8432e6e38 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/tmpcj34n6x6/images/random'
+    '/tmp/tmp3bpw5n69/images/random'
 
 
 
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
 
  .. code-block:: none
 
-    /tmp/tmpcj34n6x6/images/target contains 8144 images
-    /tmp/tmpcj34n6x6/images/random contains 5000 images
+    /tmp/tmp3bpw5n69/images/target contains 8144 images
+    /tmp/tmp3bpw5n69/images/random contains 5000 images
 
 
 
@@ -501,13 +501,13 @@ the time on our validation set).
  .. code-block:: none
 
     Epoch 1/3
-    328/328 - 55s - loss: 0.2667 - accuracy: 0.9124 - val_loss: 0.1268 - val_accuracy: 0.9558
+    328/328 - 55s - loss: 0.2374 - accuracy: 0.9198 - val_loss: 0.1366 - val_accuracy: 0.9596
     Epoch 2/3
-    328/328 - 52s - loss: 0.1080 - accuracy: 0.9607 - val_loss: 0.1114 - val_accuracy: 0.9637
+    328/328 - 52s - loss: 0.1010 - accuracy: 0.9627 - val_loss: 0.1120 - val_accuracy: 0.9641
     Epoch 3/3
-    328/328 - 52s - loss: 0.0709 - accuracy: 0.9731 - val_loss: 0.1705 - val_accuracy: 0.9464
+    328/328 - 52s - loss: 0.0697 - accuracy: 0.9747 - val_loss: 0.2233 - val_accuracy: 0.9415
 
-    <keras.callbacks.History object at 0x7fe15997f390>
+    <keras.callbacks.History object at 0x7f5ce46c9510>
 
 
 
@@ -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  50.438 seconds)
+   **Total running time of the script:** ( 4 minutes  51.736 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 e0c1852ad..d32a1edba 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,16 +5,16 @@
 
 Computation times
 =================
-**05:43.464** total execution time for **how_to_work_with_microtvm** files:
+**05:45.541** total execution time for **how_to_work_with_microtvm** files:
 
 +---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``)               | 04:50.438 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``)               | 04:51.736 | 0.0 MB |
 +---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)         | 00:41.751 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)         | 00:41.903 | 0.0 MB |
 +---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``)                   | 00:08.001 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``)                   | 00:08.607 | 0.0 MB |
 +---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)             | 00:03.271 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)             | 00:03.293 | 0.0 MB |
 +---------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``)             | 00:00.001 | 0.0 MB |
 +---------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index 90ad40bae..c80bb66bc 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
 =================
-**00:41.589** total execution time for **how_to_work_with_relay** files:
+**00:41.109** total execution time for **how_to_work_with_relay** files:
 
 +----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:30.153 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:29.861 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)           | 00:09.834 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)           | 00:09.748 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)                             | 00:01.595 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)                             | 00:01.493 | 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 2ca07f39f..b2504b8a1 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 0x7fe1592b24d0>
+    <function my_cuda_math_rule at 0x7f5caef6a8c0>
 
 
 
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 8b70b1717..c771fa0f2 100644
--- a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
@@ -5,20 +5,20 @@
 
 Computation times
 =================
-**00:04.111** total execution time for **how_to_work_with_schedules** files:
+**00:04.011** total execution time for **how_to_work_with_schedules** files:
 
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)                 | 00:01.854 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)                 | 00:01.857 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)                     | 00:01.014 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)                     | 00:00.930 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)                     | 00:00.518 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)                               | 00:00.512 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)                               | 00:00.505 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)                     | 00:00.130 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)                     | 00:00.120 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.041 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.040 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)                               | 00:00.027 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
index a3368b9b0..b09851ae5 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -347,7 +347,7 @@ The importing needs to happen before the tensorized GEMV being executed.
                  C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
       buffer_map = {A_1: A, B_1: B, C_1: C}
       preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
-      attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmppyh3n01m/input0.cc'\nsource_filename = \"/tmp/tmppyh3n01m/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/tmplfqlw9m8/input0.cc'\nsource_filename = \"/tmp/tmplfqlw9m8/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 af1ebb167..590d24e6a 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
 =================
-**00:21.199** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:21.313** total execution time for **topic_vta_tutorials_autotvm** files:
 
 +---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:21.193 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:21.306 | 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 c6c6c3334..e8ca3b114 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -291,7 +291,7 @@ The compilation steps are:
       DeprecationWarning,
     /workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the  new recommended usage.
       relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
-    resnet18_v1 inference graph built in 22.82s!
+    resnet18_v1 inference graph built in 22.80s!
 
 
 
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 2da9f46b2..502c53226 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -335,7 +335,7 @@ The compilation steps are:
       "target_host parameter is going to be deprecated. "
     /workspace/python/tvm/relay/build_module.py:411: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
       DeprecationWarning,
-    yolov3-tiny inference graph built in 15.99s!
+    yolov3-tiny inference graph built in 16.01s!
 
 
 
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 dfc5ee49d..bdc7046ee 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
 =================
-**01:31.796** total execution time for **topic_vta_tutorials_frontend** files:
+**01:31.318** total execution time for **topic_vta_tutorials_frontend** files:
 
 +------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)           | 00:48.703 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)           | 00:48.443 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:43.093 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:42.875 | 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 ba331d234..6b61881d9 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
 =================
-**00:03.244** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.223** total execution time for **topic_vta_tutorials_optimize** files:
 
 +--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)         | 00:02.855 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)         | 00:02.835 | 0.0 MB |
 +--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.389 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.388 | 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 a3e626e25..94631179d 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
 =================
-**00:00.718** total execution time for **topic_vta_tutorials** files:
+**00:00.715** total execution time for **topic_vta_tutorials** files:
 
 +---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.384 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.391 | 0.0 MB |
 +---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.334 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.325 | 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 f28b33609..1a22d8ce0 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -328,7 +328,7 @@ We build the binary and check its correctness and performance.
 
  .. code-block:: none
 
-    Execution time of this operator: 94.133 ms
+    Execution time of this operator: 92.231 ms
 
 
 
diff --git a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
index f51dbda4a..d2064cf4d 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -462,16 +462,16 @@ reduce variance, we take 5 measurements and average them.
     waiting for device...
     device available
     Get devices for measurement successfully!
-    No: 1   GFLOPS: 10.12/10.12     result: MeasureResult(costs=(0.026527394399999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5617697238922119, timestamp=1659639714.1637657)       [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
-    No: 2   GFLOPS: 2.52/10.12      result: MeasureResult(costs=(0.10634097180000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8425731658935547, timestamp=1659639716.0257695)        [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
-    No: 3   GFLOPS: 11.85/11.85     result: MeasureResult(costs=(0.0226621396,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5546488761901855, timestamp=1659639717.071295)        [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
-    No: 4   GFLOPS: 1.85/11.85      result: MeasureResult(costs=(0.1450383722,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4459638595581055, timestamp=1659639720.0794039)       [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
-    No: 5   GFLOPS: 3.70/11.85      result: MeasureResult(costs=(0.07249268680000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.292184591293335, timestamp=1659639721.5019739) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
-    No: 6   GFLOPS: 1.76/11.85      result: MeasureResult(costs=(0.1523721116,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.562816858291626, timestamp=1659639724.6312842)        [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
-    No: 7   GFLOPS: 0.87/11.85      result: MeasureResult(costs=(0.30950368279999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.066531658172607, timestamp=1659639729.7433884) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
-    No: 8   GFLOPS: 10.52/11.85     result: MeasureResult(costs=(0.0255115052,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5481798648834229, timestamp=1659639730.3131433)       [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
-    No: 9   GFLOPS: 1.60/11.85      result: MeasureResult(costs=(0.167932672,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.785961627960205, timestamp=1659639733.2173142) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
-    No: 10  GFLOPS: 2.77/11.85      result: MeasureResult(costs=(0.0970107032,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6561565399169922, timestamp=1659639734.9309878)       [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+    No: 1   GFLOPS: 11.54/11.54     result: MeasureResult(costs=(0.023254367800000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5027024745941162, timestamp=1659646522.1498861)       [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+    No: 2   GFLOPS: 2.99/11.54      result: MeasureResult(costs=(0.08978048320000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5882461071014404, timestamp=1659646523.7476647)        [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+    No: 3   GFLOPS: 12.01/12.01     result: MeasureResult(costs=(0.0223575308,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5568971633911133, timestamp=1659646524.7873862)       [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+    No: 4   GFLOPS: 1.80/12.01      result: MeasureResult(costs=(0.14952399,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.517800807952881, timestamp=1659646527.869588)   [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+    No: 5   GFLOPS: 3.72/12.01      result: MeasureResult(costs=(0.0720663812,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2833402156829834, timestamp=1659646529.280509)        [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+    No: 6   GFLOPS: 1.88/12.01      result: MeasureResult(costs=(0.1424236102,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4384822845458984, timestamp=1659646531.7613738)       [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+    No: 7   GFLOPS: 0.89/12.01      result: MeasureResult(costs=(0.3020184768,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.94750452041626, timestamp=1659646537.2712343) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+    No: 8   GFLOPS: 10.82/12.01     result: MeasureResult(costs=(0.0247996618,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5380039215087891, timestamp=1659646537.828989)        [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+    No: 9   GFLOPS: 1.77/12.01      result: MeasureResult(costs=(0.1515593636,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.53814959526062, timestamp=1659646540.485943)  [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+    No: 10  GFLOPS: 2.82/12.01      result: MeasureResult(costs=(0.095165439,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.642676830291748, timestamp=1659646542.1685784) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
 
 
 
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index ff859a379..1a8b238fb 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -327,7 +327,7 @@ standard deviation.
 
  .. code-block:: none
 
-    {'mean': 493.08102606999455, 'median': 492.9313444999707, 'std': 0.6852841328006576}
+    {'mean': 492.7949012599993, 'median': 492.77268674999846, 'std': 0.5315715046600841}
 
 
 
@@ -563,30 +563,30 @@ the tuning data to.
 
     /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-
    [Task  1/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  1/25]  Current/Best:   17.56/  17.56 GFLOPS | Progress: (4/20) | 6.31 s
    [Task  1/25]  Current/Best:    6.17/  17.56 GFLOPS | Progress: (8/20) | 9.31 s
    [Task  1/25]  Current/Best:   11.57/  22.74 GFLOPS | Progress: (12/20) | 11.73 s
    [Task  1/25]  Current/Best:   16.92/  22.84 GFLOPS | Progress: (16/20) | 13.41 s
    [Task  1/25]  Current/Best:   11.60/  23.94 GFLOPS | Progress: (20/20) | 15.14 s Done.
-
    [Task  2/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  2/25]  Current/Best:   12.12/  13.05 GFLOPS | Progress: (4/20) | 3.78 s
    [Task  2/25]  Current/Best:   14.16/  18.59 GFLOPS | Progress: (8/20) | 5.10 s
    [Task  2/25]  Current/Best:   21.01/  21.01 GFLOPS | Progress: (12/20) | 6.42 s
    [Task  2/25]  Current/Best:   12.40/  21.01 GFLOPS | Progress: (16/20) | 7.68 s
    [Task  2/25]  Current/Best:   19.27/  21.01 GFLOPS | Progress: (20/20) | 9.28 s Done.
-
    [Task  3/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  3/25]  Current/Best:    1.63/  10.53 GFLOPS | Progress: (4/20) | 5.87 s
    [Task  3/25]  Current/Best:   15.60/  16.85 GFLOPS | Progress: (8/20) | 7.80 s
    [Task  3/25]  Current/Best:   14.89/  16.85 GFLOPS | Progress: (12/20) | 9.54 s
    [Task  3/25]  Current/Best:    7.20/  23.79 GFLOPS | Progress: (16/20) | 11.47 s
    [Task  3/25]  Current/Best:   12.66/  23.79 GFLOPS | Progress: (20/20) | 15.97 s Done.
-
    [Task  4/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  4/25]  Current/Best:    9.56/  20.57 GFLOPS | Progress: (4/20) | 2.38 s
    [Task  4/25]  Current/Best:    6.86/  20.57 GFLOPS | Progress: (8/20) | 6.68 s
    [Task  4/25]  Current/Best:   22.32/  22.32 GFLOPS | Progress: (12/20) | 11.10 s
    [Task  4/25]  Current/Best:   17.47/  22.32 GFLOPS | Progress: (16/20) | 13.35 s
    [Task  4/25]  Current/Best:   13.54/  22.32 GFLOPS | Progress: (20/20) | 15.32 s Done.
-
    [Task  5/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  5/25]  Current/Best:    9.51/  10.30 GFLOPS | Progress: (4/20) | 2.59 s
    [Task  5/25]  Current/Best:   11.68/  12.41 GFLOPS | Progress: (8/20) | 4.66 s
    [Task  5/25]  Current/Best:   11.58/  17.99 GFLOPS | Progress: (12/20) | 7.59 s
    [Task  5/25]  Current/Best:   11.64/  22.64 GFLOPS | Progress: (16/20) | 9.01 s
    [Task  5/25]  Current/Best:   11.96/  22.64 GFLOPS | Progress: (20/20) | 10.87 s Done.
-
    [Task  6/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  6/25]  Current/Best:   12.27/  20.77 GFLOPS | Progress: (4/20) | 3.98 s
    [Task  6/25]  Current/Best:   17.51/  20.77 GFLOPS | Progress: (8/20) | 5.75 s
    [Task  6/25]  Current/Best:   13.31/  20.77 GFLOPS | Progress: (12/20) | 7.68 s
    [Task  6/25]  Current/Best:   20.01/  20.77 GFLOPS | Progress: (16/20) | 9.96 s
    [Task  6/25]  Current/Best:    3.72/  20.77 GFLOPS | Progress: (20/20) | 12.50 s Done.
-
    [Task  7/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  7/25]  Current/Best:   11.23/  12.88 GFLOPS | Progress: (4/20) | 3.61 s
    [Task  7/25]  Current/Best:   20.26/  21.07 GFLOPS | Progress: (8/20) | 5.12 s
    [Task  7/25]  Current/Best:   16.11/  21.07 GFLOPS | Progress: (12/20) | 7.05 s
    [Task  7/25]  Current/Best:   12.27/  21.07 GFLOPS | Progress: (16/20) | 9.10 s
    [Task  7/25]  Current/Best:    6.44/  21.80 GFLOPS | Progress: (20/20) | 11.55 s Done.
-
    [Task  8/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  8/25]  Current/Best:    9.71/  13.70 GFLOPS | Progress: (4/20) | 2.91 s
    [Task  8/25]  Current/Best:    9.17/  13.70 GFLOPS | Progress: (8/20) | 7.62 s
    [Task  8/25]  Current/Best:   12.73/  13.70 GFLOPS | Progress: (12/20) | 13.71 s
    [Task  8/25]  Current/Best:   18.68/  18.68 GFLOPS | Progress: (16/20) | 15.80 s
    [Task  8/25]  Current/Best:   19.84/  19.84 GFLOPS | Progress: (20/20) | 22.27 s Done.
-
    [Task  9/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  9/25]  Current/Best:   14.34/  15.74 GFLOPS | Progress: (4/20) | 11.95 s
    [Task  9/25]  Current/Best:   23.43/  23.43 GFLOPS | Progress: (8/20) | 13.80 s
    [Task  9/25]  Current/Best:    8.24/  23.43 GFLOPS | Progress: (12/20) | 16.16 s
    [Task  9/25]  Current/Best:   18.06/  23.43 GFLOPS | Progress: (16/20) | 18.72 s
    [Task  9/25]  Current/Best:    9.24/  23.43 GFLOPS | Progress: (20/20) | 26.39 s
    [Task 10/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 10/25]  Current/Best:   18.18/  18.18 GFLOPS | Progress: (4/20) | 2.57 s
    [Task 10/25]  Current/Best:   15.57/  18.18 GFLOPS | Progress: (8/20) | 4.15 s
    [Task 10/25]  Current/Best:   12.33/  18.92 GFLOPS | Progress: (12/20) | 5.67 s
    [Task 10/25]  Current/Best:   18.98/  20.15 GFLOPS | Progress: (16/20) | 6.79 s
    [Task 10/25]  Current/Best:    8.85/  20.15 GFLOPS | Progress: (20/20
 ) | 8.34 s Done.
-
    [Task 11/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 11/25]  Current/Best:   12.28/  18.15 GFLOPS | Progress: (4/20) | 3.26 s
    [Task 11/25]  Current/Best:   14.87/  18.15 GFLOPS | Progress: (8/20) | 6.03 s
    [Task 11/25]  Current/Best:   18.17/  18.17 GFLOPS | Progress: (12/20) | 8.10 s
    [Task 11/25]  Current/Best:   13.52/  21.23 GFLOPS | Progress: (16/20) | 10.81 s
    [Task 11/25]  Current/Best:   19.41/  21.62 GFLOPS | Progress: (20/20) | 12.81 s Done.
-
    [Task 12/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 12/25]  Current/Best:    7.82/  18.15 GFLOPS | Progress: (4/20) | 5.34 s
    [Task 12/25]  Current/Best:    5.18/  18.15 GFLOPS | Progress: (8/20) | 9.05 s
    [Task 12/25]  Current/Best:   18.86/  18.88 GFLOPS | Progress: (12/20) | 11.03 s
    [Task 12/25]  Current/Best:   15.44/  18.88 GFLOPS | Progress: (16/20) | 13.82 s
    [Task 12/25]  Current/Best:   15.12/  18.88 GFLOPS | Progress: (20/20) | 15.73 s Done.
-
    [Task 13/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 13/25]  Current/Best:    8.92/  17.29 GFLOPS | Progress: (4/20) | 3.65 s
    [Task 13/25]  Current/Best:   15.73/  20.98 GFLOPS | Progress: (8/20) | 6.08 s
    [Task 13/25]  Current/Best:   19.61/  21.75 GFLOPS | Progress: (12/20) | 8.93 s
    [Task 13/25]  Current/Best:   12.26/  21.75 GFLOPS | Progress: (16/20) | 12.35 s
    [Task 13/25]  Current/Best:   18.58/  21.75 GFLOPS | Progress: (20/20) | 14.62 s Done.
-
    [Task 14/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 14/25]  Current/Best:   12.03/  13.29 GFLOPS | Progress: (4/20) | 3.36 s
    [Task 14/25]  Current/Best:    6.09/  13.39 GFLOPS | Progress: (8/20) | 5.55 s
    [Task 14/25]  Current/Best:   20.70/  20.70 GFLOPS | Progress: (12/20) | 8.07 s
    [Task 14/25]  Current/Best:   16.28/  20.70 GFLOPS | Progress: (16/20) | 9.72 s Done.
-
    [Task 14/25]  Current/Best:   17.56/  20.70 GFLOPS | Progress: (20/20) | 11.52 s
    [Task 15/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 15/25]  Current/Best:   16.16/  17.66 GFLOPS | Progress: (4/20) | 2.70 s
    [Task 15/25]  Current/Best:   14.53/  18.04 GFLOPS | Progress: (8/20) | 4.05 s
    [Task 15/25]  Current/Best:   10.39/  22.29 GFLOPS | Progress: (12/20) | 6.10 s
    [Task 15/25]  Current/Best:   20.43/  22.29 GFLOPS | Progress: (16/20) | 9.43 s
    [Task 15/25]  Current/Best:    9.63/  22.29 GFLOPS | Progress: (20/20) | 10.45 s
    [Task 16/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 16/25]  Current/Best:   20.36/  20.36 GFLOPS | Progress: (4/20) | 2.98 s
    [Task 16/25]  Current/Best:    3.04/  20.36 GFLOPS | Progress: (8/20) | 4.59 s
    [Task 16/25]  Current/Best:   19.38/  20.36 GFLOPS | Progress: (12/20) | 5.79 s
    [Task 16/25]  Current/Best:   17.96/  20.36 GFLOPS | Progress: (16/20) |
  7.14 s
    [Task 16/25]  Current/Best:   10.03/  21.12 GFLOPS | Progress: (20/20) | 9.19 s Done.
-
    [Task 17/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 17/25]  Current/Best:   13.23/  18.70 GFLOPS | Progress: (4/20) | 4.69 s
    [Task 17/25]  Current/Best:   13.92/  23.42 GFLOPS | Progress: (8/20) | 7.54 s
    [Task 17/25]  Current/Best:   16.87/  23.42 GFLOPS | Progress: (12/20) | 9.60 s
    [Task 17/25]  Current/Best:   16.58/  23.42 GFLOPS | Progress: (16/20) | 11.73 s
    [Task 17/25]  Current/Best:   10.05/  23.42 GFLOPS | Progress: (20/20) | 13.83 s Done.
-
    [Task 18/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 18/25]  Current/Best:   11.24/  17.03 GFLOPS | Progress: (4/20) | 3.69 s
    [Task 18/25]  Current/Best:   10.53/  19.56 GFLOPS | Progress: (8/20) | 7.09 s
    [Task 18/25]  Current/Best:   19.50/  19.56 GFLOPS | Progress: (12/20) | 9.04 s
    [Task 18/25]  Current/Best:   10.06/  19.56 GFLOPS | Progress: (16/20) | 12.58 s
    [Task 18/25]  Current/Best:   20.64/  20.64 GFLOPS | Progress: (20/20) | 14.07 s Done.
-
    [Task 19/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 19/25]  Current/Best:    7.05/  20.37 GFLOPS | Progress: (4/20) | 6.01 s
    [Task 19/25]  Current/Best:    2.60/  20.37 GFLOPS | Progress: (8/20) | 9.24 s
    [Task 19/25]  Current/Best:   19.40/  21.75 GFLOPS | Progress: (12/20) | 12.06 s
    [Task 19/25]  Current/Best:   14.20/  21.75 GFLOPS | Progress: (16/20) | 14.92 s
    [Task 19/25]  Current/Best:    2.70/  23.53 GFLOPS | Progress: (20/20) | 17.72 s Done.
-
    [Task 20/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 20/25]  Current/Best:    9.01/  15.07 GFLOPS | Progress: (4/20) | 3.34 s Done.
+
    [Task  1/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  1/25]  Current/Best:   17.53/  17.53 GFLOPS | Progress: (4/20) | 6.26 s
    [Task  1/25]  Current/Best:    6.17/  17.53 GFLOPS | Progress: (8/20) | 9.25 s
    [Task  1/25]  Current/Best:   11.56/  22.70 GFLOPS | Progress: (12/20) | 11.70 s
    [Task  1/25]  Current/Best:   16.78/  22.86 GFLOPS | Progress: (16/20) | 13.39 s
    [Task  1/25]  Current/Best:   11.63/  23.90 GFLOPS | Progress: (20/20) | 15.14 s Done.
+
    [Task  2/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  2/25]  Current/Best:   12.37/  13.20 GFLOPS | Progress: (4/20) | 3.76 s
    [Task  2/25]  Current/Best:   14.22/  18.95 GFLOPS | Progress: (8/20) | 5.07 s
    [Task  2/25]  Current/Best:   21.19/  21.19 GFLOPS | Progress: (12/20) | 6.38 s
    [Task  2/25]  Current/Best:   12.47/  21.19 GFLOPS | Progress: (16/20) | 7.67 s
    [Task  2/25]  Current/Best:   19.38/  21.19 GFLOPS | Progress: (20/20) | 9.28 s Done.
+
    [Task  3/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  3/25]  Current/Best:    1.63/  10.58 GFLOPS | Progress: (4/20) | 5.87 s
    [Task  3/25]  Current/Best:   15.46/  16.86 GFLOPS | Progress: (8/20) | 7.81 s
    [Task  3/25]  Current/Best:   14.87/  16.86 GFLOPS | Progress: (12/20) | 9.51 s
    [Task  3/25]  Current/Best:    7.20/  23.82 GFLOPS | Progress: (16/20) | 11.42 s
    [Task  3/25]  Current/Best:   11.74/  23.82 GFLOPS | Progress: (20/20) | 15.97 s Done.
+
    [Task  4/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  4/25]  Current/Best:    9.57/  20.42 GFLOPS | Progress: (4/20) | 2.38 s
    [Task  4/25]  Current/Best:    6.86/  20.42 GFLOPS | Progress: (8/20) | 7.06 s
    [Task  4/25]  Current/Best:   22.49/  22.49 GFLOPS | Progress: (12/20) | 12.04 s
    [Task  4/25]  Current/Best:   17.26/  22.49 GFLOPS | Progress: (16/20) | 14.41 s
    [Task  4/25]  Current/Best:   13.29/  22.49 GFLOPS | Progress: (20/20) | 16.49 s Done.
+
    [Task  5/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  5/25]  Current/Best:    9.77/  10.44 GFLOPS | Progress: (4/20) | 2.58 s
    [Task  5/25]  Current/Best:   11.84/  12.75 GFLOPS | Progress: (8/20) | 4.64 s
    [Task  5/25]  Current/Best:   11.48/  17.98 GFLOPS | Progress: (12/20) | 7.85 s
    [Task  5/25]  Current/Best:   11.89/  22.87 GFLOPS | Progress: (16/20) | 9.27 s
    [Task  5/25]  Current/Best:   12.04/  22.87 GFLOPS | Progress: (20/20) | 11.20 s Done.
+
    [Task  6/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  6/25]  Current/Best:   12.29/  20.66 GFLOPS | Progress: (4/20) | 4.10 s
    [Task  6/25]  Current/Best:   19.13/  20.66 GFLOPS | Progress: (8/20) | 5.87 s
    [Task  6/25]  Current/Best:   13.18/  20.66 GFLOPS | Progress: (12/20) | 7.82 s
    [Task  6/25]  Current/Best:   20.04/  20.66 GFLOPS | Progress: (16/20) | 10.05 s
    [Task  6/25]  Current/Best:    3.74/  20.66 GFLOPS | Progress: (20/20) | 12.59 s Done.
+
    [Task  7/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  7/25]  Current/Best:    9.84/  12.96 GFLOPS | Progress: (4/20) | 3.64 s
    [Task  7/25]  Current/Best:   20.34/  21.05 GFLOPS | Progress: (8/20) | 5.15 s
    [Task  7/25]  Current/Best:   15.91/  21.05 GFLOPS | Progress: (12/20) | 7.05 s
    [Task  7/25]  Current/Best:   12.29/  21.05 GFLOPS | Progress: (16/20) | 9.08 s
    [Task  7/25]  Current/Best:    6.32/  21.74 GFLOPS | Progress: (20/20) | 11.53 s Done.
+
    [Task  8/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  8/25]  Current/Best:    9.97/  14.12 GFLOPS | Progress: (4/20) | 2.92 s
    [Task  8/25]  Current/Best:    9.47/  14.12 GFLOPS | Progress: (8/20) | 7.95 s
    [Task  8/25]  Current/Best:   12.70/  14.12 GFLOPS | Progress: (12/20) | 14.36 s
    [Task  8/25]  Current/Best:   18.82/  18.82 GFLOPS | Progress: (16/20) | 16.46 s
    [Task  8/25]  Current/Best:   20.04/  20.04 GFLOPS | Progress: (20/20) | 23.53 s Done.
+
    [Task  9/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  9/25]  Current/Best:   14.38/  15.72 GFLOPS | Progress: (4/20) | 11.96 s
    [Task  9/25]  Current/Best:   23.54/  23.54 GFLOPS | Progress: (8/20) | 13.71 s
    [Task  9/25]  Current/Best:    8.28/  23.54 GFLOPS | Progress: (12/20) | 16.24 s
    [Task  9/25]  Current/Best:   18.01/  23.54 GFLOPS | Progress: (16/20) | 19.08 s
    [Task  9/25]  Current/Best:    9.24/  23.54 GFLOPS | Progress: (20/20) | 27.60 s
    [Task 10/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 10/25]  Current/Best:   18.16/  18.16 GFLOPS | Progress: (4/20) | 2.54 s
    [Task 10/25]  Current/Best:   15.49/  18.16 GFLOPS | Progress: (8/20) | 4.17 s
    [Task 10/25]  Current/Best:   12.54/  18.95 GFLOPS | Progress: (12/20) | 5.71 s
    [Task 10/25]  Current/Best:   19.14/  20.38 GFLOPS | Progress: (16/20) | 6.82 s
    [Task 10/25]  Current/Best:    8.92/  20.38 GFLOPS | Progress: (20/20
 ) | 8.37 s Done.
+
    [Task 11/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 11/25]  Current/Best:   12.34/  18.12 GFLOPS | Progress: (4/20) | 3.31 s
    [Task 11/25]  Current/Best:   16.92/  18.12 GFLOPS | Progress: (8/20) | 6.10 s
    [Task 11/25]  Current/Best:   16.54/  18.12 GFLOPS | Progress: (12/20) | 8.14 s
    [Task 11/25]  Current/Best:   13.36/  21.22 GFLOPS | Progress: (16/20) | 11.09 s
    [Task 11/25]  Current/Best:   19.43/  21.62 GFLOPS | Progress: (20/20) | 13.15 s Done.
+
    [Task 12/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 12/25]  Current/Best:    7.83/  18.27 GFLOPS | Progress: (4/20) | 5.70 s
    [Task 12/25]  Current/Best:    5.26/  18.27 GFLOPS | Progress: (8/20) | 9.58 s
    [Task 12/25]  Current/Best:   19.04/  19.04 GFLOPS | Progress: (12/20) | 11.56 s
    [Task 12/25]  Current/Best:   15.54/  19.04 GFLOPS | Progress: (16/20) | 14.46 s
    [Task 12/25]  Current/Best:   15.16/  19.04 GFLOPS | Progress: (20/20) | 16.37 s Done.
+
    [Task 13/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 13/25]  Current/Best:    8.76/  17.32 GFLOPS | Progress: (4/20) | 3.75 s
    [Task 13/25]  Current/Best:   16.14/  20.92 GFLOPS | Progress: (8/20) | 6.34 s
    [Task 13/25]  Current/Best:   19.54/  21.34 GFLOPS | Progress: (12/20) | 9.45 s
    [Task 13/25]  Current/Best:   12.22/  21.34 GFLOPS | Progress: (16/20) | 12.89 s
    [Task 13/25]  Current/Best:   18.96/  21.34 GFLOPS | Progress: (20/20) | 15.22 s Done.
+
    [Task 14/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 14/25]  Current/Best:   13.65/  13.65 GFLOPS | Progress: (4/20) | 3.42 s
    [Task 14/25]  Current/Best:    6.12/  13.65 GFLOPS | Progress: (8/20) | 5.61 s
    [Task 14/25]  Current/Best:   19.94/  19.94 GFLOPS | Progress: (12/20) | 8.25 s
    [Task 14/25]  Current/Best:   16.43/  19.94 GFLOPS | Progress: (16/20) | 9.90 s Done.
+
    [Task 14/25]  Current/Best:   17.33/  19.94 GFLOPS | Progress: (20/20) | 11.66 s
    [Task 15/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 15/25]  Current/Best:   16.17/  17.66 GFLOPS | Progress: (4/20) | 2.71 s
    [Task 15/25]  Current/Best:   13.07/  18.06 GFLOPS | Progress: (8/20) | 4.07 s
    [Task 15/25]  Current/Best:   10.41/  22.34 GFLOPS | Progress: (12/20) | 6.28 s
    [Task 15/25]  Current/Best:   20.40/  22.34 GFLOPS | Progress: (16/20) | 9.34 s
    [Task 15/25]  Current/Best:    9.66/  22.34 GFLOPS | Progress: (20/20) | 10.36 s
    [Task 16/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 16/25]  Current/Best:   20.39/  20.39 GFLOPS | Progress: (4/20) | 2.95 s
    [Task 16/25]  Current/Best:    3.04/  20.39 GFLOPS | Progress: (8/20) | 4.55 s
    [Task 16/25]  Current/Best:   19.54/  20.39 GFLOPS | Progress: (12/20) | 5.75 s
    [Task 16/25]  Current/Best:   17.97/  20.39 GFLOPS | Progress: (16/20) |
  7.12 s
    [Task 16/25]  Current/Best:   10.04/  22.32 GFLOPS | Progress: (20/20) | 9.26 s Done.
+
    [Task 17/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 17/25]  Current/Best:   13.17/  17.01 GFLOPS | Progress: (4/20) | 4.79 s
    [Task 17/25]  Current/Best:   14.33/  23.27 GFLOPS | Progress: (8/20) | 7.70 s
    [Task 17/25]  Current/Best:   16.86/  23.27 GFLOPS | Progress: (12/20) | 9.76 s
    [Task 17/25]  Current/Best:   16.43/  23.27 GFLOPS | Progress: (16/20) | 11.96 s
    [Task 17/25]  Current/Best:   10.05/  23.27 GFLOPS | Progress: (20/20) | 14.11 s Done.
+
    [Task 18/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 18/25]  Current/Best:   11.33/  18.22 GFLOPS | Progress: (4/20) | 3.79 s
    [Task 18/25]  Current/Best:   10.57/  18.22 GFLOPS | Progress: (8/20) | 7.44 s
    [Task 18/25]  Current/Best:   18.77/  18.77 GFLOPS | Progress: (12/20) | 9.37 s
    [Task 18/25]  Current/Best:    9.98/  18.77 GFLOPS | Progress: (16/20) | 13.26 s
    [Task 18/25]  Current/Best:   20.57/  20.57 GFLOPS | Progress: (20/20) | 14.76 s Done.
+
    [Task 19/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 19/25]  Current/Best:    6.90/  20.48 GFLOPS | Progress: (4/20) | 6.11 s
    [Task 19/25]  Current/Best:    2.61/  20.48 GFLOPS | Progress: (8/20) | 9.43 s
    [Task 19/25]  Current/Best:   19.83/  21.37 GFLOPS | Progress: (12/20) | 12.33 s
    [Task 19/25]  Current/Best:   14.10/  21.52 GFLOPS | Progress: (16/20) | 15.31 s
    [Task 19/25]  Current/Best:    2.70/  23.68 GFLOPS | Progress: (20/20) | 18.07 s Done.
+
    [Task 20/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 20/25]  Current/Best:    9.01/  15.30 GFLOPS | Progress: (4/20) | 3.31 s Done.
      Done.
-
    [Task 20/25]  Current/Best:    9.79/  15.07 GFLOPS | Progress: (8/20) | 6.62 s
    [Task 20/25]  Current/Best:    2.32/  16.70 GFLOPS | Progress: (12/20) | 10.52 s
    [Task 20/25]  Current/Best:   12.51/  16.70 GFLOPS | Progress: (16/20) | 14.23 s
    [Task 20/25]  Current/Best:   13.56/  22.32 GFLOPS | Progress: (20/20) | 16.28 s
    [Task 21/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 21/25]  Current/Best:    6.40/  17.71 GFLOPS | Progress: (4/20) | 3.22 s
    [Task 21/25]  Current/Best:   14.63/  17.71 GFLOPS | Progress: (8/20) | 4.78 s
    [Task 21/25]  Current/Best:    1.61/  17.71 GFLOPS | Progress: (12/20) | 6.94 s
    [Task 21/25]  Current/Best:   18.06/  18.06 GFLOPS | Progress: (16/20) | 10.36 s
    [Task 21/25]  Current/Best:    4.47/  18.06 GFLOPS | Progress: (20/20) | 17.47 s
    [Task 22/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 22/25]  Current/Best:    2.70/  17.03 GFLOPS | Progress: (4/20
 ) | 2.67 s
    [Task 22/25]  Current/Best:    8.60/  22.06 GFLOPS | Progress: (8/20) | 4.57 s
    [Task 22/25]  Current/Best:   19.76/  22.06 GFLOPS | Progress: (12/20) | 6.89 s
    [Task 22/25]  Current/Best:   15.05/  22.06 GFLOPS | Progress: (16/20) | 8.91 s
    [Task 22/25]  Current/Best:   14.11/  22.06 GFLOPS | Progress: (20/20) | 10.63 s Done.
-
    [Task 23/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 23/25]  Current/Best:   17.59/  20.78 GFLOPS | Progress: (4/20) | 3.26 s
    [Task 23/25]  Current/Best:   14.65/  20.78 GFLOPS | Progress: (8/20) | 6.62 s
    [Task 23/25]  Current/Best:   20.73/  21.77 GFLOPS | Progress: (12/20) | 8.41 s
    [Task 23/25]  Current/Best:    6.29/  21.77 GFLOPS | Progress: (16/20) | 15.52 s
    [Task 23/25]  Current/Best:    7.82/  21.77 GFLOPS | Progress: (20/20) | 19.71 s Done.
-
    [Task 24/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 24/25]  Current/Best:    8.36/   8.36 GFLOPS | Progress: (4/20) | 11.80 s
    [Task 24/25]  Current/Best:    2.15/   8.36 GFLOPS | Progress: (8/20) | 22.85 s
    [Task 24/25]  Current/Best:    4.28/   8.36 GFLOPS | Progress: (12/20) | 34.37 s Done.
-
    [Task 24/25]  Current/Best:    5.93/   8.65 GFLOPS | Progress: (16/20) | 39.69 s
    [Task 24/25]  Current/Best:    3.34/   8.79 GFLOPS | Progress: (20/20) | 45.65 s Done.
-
    [Task 25/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 25/25]  Current/Best:    1.55/   2.79 GFLOPS | Progress: (4/20) | 11.61 s
    [Task 25/25]  Current/Best:    5.68/   7.76 GFLOPS | Progress: (8/20) | 22.85 s
    [Task 25/25]  Current/Best:    5.96/   7.76 GFLOPS | Progress: (12/20) | 34.12 s
    [Task 25/25]  Current/Best:    5.81/   8.98 GFLOPS | Progress: (16/20) | 35.85 s
    [Task 25/25]  Current/Best:    2.83/   9.15 GFLOPS | Progress: (20/20) | 46.51 s
+
    [Task 20/25]  Current/Best:    9.79/  15.30 GFLOPS | Progress: (8/20) | 6.74 s
    [Task 20/25]  Current/Best:    2.32/  16.89 GFLOPS | Progress: (12/20) | 10.61 s
    [Task 20/25]  Current/Best:   12.58/  16.89 GFLOPS | Progress: (16/20) | 14.31 s
    [Task 20/25]  Current/Best:   11.79/  22.00 GFLOPS | Progress: (20/20) | 16.41 s
    [Task 21/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 21/25]  Current/Best:    6.40/  17.74 GFLOPS | Progress: (4/20) | 3.27 s
    [Task 21/25]  Current/Best:   14.66/  17.74 GFLOPS | Progress: (8/20) | 4.86 s
    [Task 21/25]  Current/Best:    1.61/  17.74 GFLOPS | Progress: (12/20) | 7.01 s
    [Task 21/25]  Current/Best:   17.84/  17.84 GFLOPS | Progress: (16/20) | 10.54 s
    [Task 21/25]  Current/Best:    4.47/  17.84 GFLOPS | Progress: (20/20) | 17.81 s
    [Task 22/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 22/25]  Current/Best:    2.70/  17.01 GFLOPS | Progress: (4/20
 ) | 2.67 s
    [Task 22/25]  Current/Best:    8.70/  22.02 GFLOPS | Progress: (8/20) | 4.65 s
    [Task 22/25]  Current/Best:   19.56/  22.02 GFLOPS | Progress: (12/20) | 7.04 s
    [Task 22/25]  Current/Best:   15.44/  22.02 GFLOPS | Progress: (16/20) | 9.17 s
    [Task 22/25]  Current/Best:   14.63/  22.02 GFLOPS | Progress: (20/20) | 10.89 s Done.
+
    [Task 23/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 23/25]  Current/Best:   17.70/  20.94 GFLOPS | Progress: (4/20) | 3.28 s
    [Task 23/25]  Current/Best:   14.57/  20.94 GFLOPS | Progress: (8/20) | 6.74 s
    [Task 23/25]  Current/Best:   21.32/  21.32 GFLOPS | Progress: (12/20) | 8.55 s
    [Task 23/25]  Current/Best:    6.57/  21.32 GFLOPS | Progress: (16/20) | 15.56 s
    [Task 23/25]  Current/Best:    8.15/  21.32 GFLOPS | Progress: (20/20) | 19.69 s Done.
+
    [Task 24/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 24/25]  Current/Best:    8.94/   8.94 GFLOPS | Progress: (4/20) | 11.79 s
    [Task 24/25]  Current/Best:    2.15/   8.94 GFLOPS | Progress: (8/20) | 22.77 s
    [Task 24/25]  Current/Best:    4.57/   8.94 GFLOPS | Progress: (12/20) | 34.27 s Done.
+
    [Task 24/25]  Current/Best:    6.38/   8.94 GFLOPS | Progress: (16/20) | 39.91 s
    [Task 24/25]  Current/Best:    3.44/   8.94 GFLOPS | Progress: (20/20) | 45.80 s Done.
+
    [Task 25/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 25/25]  Current/Best:    1.57/   2.95 GFLOPS | Progress: (4/20) | 11.58 s
    [Task 25/25]  Current/Best:    5.90/   8.45 GFLOPS | Progress: (8/20) | 22.85 s
    [Task 25/25]  Current/Best:    5.95/   8.45 GFLOPS | Progress: (12/20) | 34.23 s
    [Task 25/25]  Current/Best:    5.84/   9.39 GFLOPS | Progress: (16/20) | 35.94 s
    [Task 25/25]  Current/Best:    2.92/   9.39 GFLOPS | Progress: (20/20) | 46.62 s
 
 
 
@@ -748,8 +748,8 @@ improvement in comparing the optimized model to the unoptimized model.
 
  .. code-block:: none
 
-    optimized: {'mean': 409.60669237000275, 'median': 408.862635950004, 'std': 1.8723862551091004}
-    unoptimized: {'mean': 493.08102606999455, 'median': 492.9313444999707, 'std': 0.6852841328006576}
+    optimized: {'mean': 397.1788065399983, 'median': 396.51443220000147, 'std': 1.663312213932835}
+    unoptimized: {'mean': 492.7949012599993, 'median': 492.77268674999846, 'std': 0.5315715046600841}
 
 
 
@@ -772,7 +772,7 @@ profiling/benchmarking.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 10 minutes  14.369 seconds)
+   **Total running time of the script:** ( 10 minutes  23.040 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 08e6b74c8..403d3684a 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -282,7 +282,7 @@ device and returns the measured cost. Network overhead is excluded.
 
  .. code-block:: none
 
-    1.458e-07 secs/op
+    1.201e-07 secs/op
 
 
 
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 444418564..d6303b092 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -263,7 +263,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
 
  .. code-block:: none
 
-    [stage(a, placeholder(a, 0x22cc11a0)), stage(b, placeholder(b, 0xc96ada0)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min [...]
+    [stage(a, placeholder(a, 0xd9b38e0)), stage(b, placeholder(b, 0x225481b0)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min [...]
 
 
 
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index 6c489505d..4aed25ffe 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,30 +5,30 @@
 
 Computation times
 =================
-**13:07.745** total execution time for **tutorial** files:
+**13:07.833** total execution time for **tutorial** files:
 
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)                 | 10:14.369 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)                 | 10:23.040 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)     | 01:01.065 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)     | 00:58.748 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 00:56.530 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 00:50.870 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)                 | 00:30.210 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)                 | 00:29.757 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)               | 00:24.234 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)               | 00:23.421 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)                               | 00:00.691 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)       | 00:01.154 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)       | 00:00.499 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)                               | 00:00.692 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.141 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.144 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``)                           | 00:00.005 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``)                             | 00:00.001 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_install.py` (``install.py``)                                     | 00:00.001 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``)   | 00:00.001 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_install.py` (``install.py``)                                     | 00:00.001 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``)                             | 00:00.001 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index f6f67469e..4325e3764 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -301,8 +301,8 @@ helper function to run a profile of the TVM generated code.
 
  .. code-block:: none
 
-    Numpy running time: 0.000008
-    naive: 0.000009
+    Numpy running time: 0.000007
+    naive: 0.000006
 
 
 
@@ -403,7 +403,7 @@ compile and run this new schedule with the parallel operation applied:
 
     /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-    parallel: 0.000009
+    parallel: 0.000006
 
 
 
@@ -460,7 +460,7 @@ factor to be the number of threads on your CPU.
 
     /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-    vector: 0.000025
+    vector: 0.000024
     @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, [(stride: int32*n: int32)], [], type="auto"),
@@ -512,10 +512,10 @@ We can now compare the different schedules
  .. code-block:: none
 
                 Operator                  Timing             Performance
-                   numpy    7.506309998461802e-06                    1.0
-                   naive    9.239200000000001e-06     1.2308577719136706
-                parallel              8.8606e-06      1.1804202067081855
-                  vector    2.4591400000000003e-05     3.276097044358585
+                   numpy    6.9266200011952605e-06                   1.0
+                   naive              5.8348e-06      0.8423733363448759
+                parallel              5.8559e-06      0.8454195551350447
+                  vector    2.3856499999999998e-05    3.4441762354342105
 
 
 
@@ -936,7 +936,7 @@ matrix multiplication.
 
  .. code-block:: none
 
-    Numpy running time: 0.018192
+    Numpy running time: 0.016793
 
 
 
@@ -996,7 +996,7 @@ optimizations.
 
     /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-    none: 3.449567
+    none: 3.291345
 
 
 
@@ -1101,7 +1101,7 @@ schedule.
 
     /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-    blocking: 0.286718
+    blocking: 0.294843
 
 
 
@@ -1199,7 +1199,7 @@ already cache friendly from our previous optimizations.
 
     /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-    vectorization: 0.330775
+    vectorization: 0.334288
     @main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
       attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
       buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1275,7 +1275,7 @@ more cache friendly.
 
     /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-    loop permutation: 0.117269
+    loop permutation: 0.112057
     @main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
       attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
       buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1376,7 +1376,7 @@ optimized schedule.
 
     /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-    array packing: 0.109018
+    array packing: 0.106499
     @main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
       attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
       buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1471,7 +1471,7 @@ to `C` when all the block results are ready.
 
     /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-    block caching: 0.110431
+    block caching: 0.102391
     @main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
       attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
       buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1559,7 +1559,7 @@ of thread-level parallelization.
 
     /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-    parallelization: 0.144564
+    parallelization: 0.134030
     @main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
       attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
       buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1640,13 +1640,13 @@ working, we can compare the results.
  .. code-block:: none
 
                 Operator                  Timing             Performance
-                    none            3.4495668072                     1.0
-                blocking     0.28671782990000005     0.08311705379978647
-           vectorization     0.33077472939999997      0.0958887732539636
-        loop permutation            0.1172686762     0.03399518918005433
-           array packing     0.10901774150000001     0.03160331357330322
-           block caching            0.1104314359    0.032013131524081646
-         parallelization            0.1445644901     0.04190801285490755
+                    none            3.2913449831                     1.0
+                blocking            0.2948428185      0.0895812562991492
+           vectorization            0.3342876312      0.1015656617329571
+        loop permutation     0.11205738779999999     0.03404607793330043
+           array packing            0.1064986515    0.032357182868048284
+           block caching            0.1023906918    0.031109073137499513
+         parallelization            0.1340297455    0.040721876979836424
 
 
 
@@ -1686,11 +1686,6 @@ operations with tunable parameters that allows you to automatically optimize
 the computation for specific platforms.
 
 
-.. rst-class:: sphx-glr-timing
-
-   **Total running time of the script:** ( 1 minutes  1.065 seconds)
-
-
 .. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
 
 .. only:: html
diff --git a/docs/commit_hash b/docs/commit_hash
index 9597daf39..56dcbad1a 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-cfa55251b2163b77e98726e73c4c3298b1903899
+2866f315f9899a49917e1a9adda21fc15841ee55
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index f99bc1364..b40b3095d 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -574,7 +574,7 @@ class:[&#39;truck 0.9266&#39;] left:471 top:83 right:689 bottom:169
 class:[&#39;bicycle 0.9984&#39;] left:111 top:113 right:577 bottom:447
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  1.434 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  1.268 seconds)</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-darknet-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/7716f96385bd5abb6e822041e285be54/from_darknet.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_darknet.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 5adc44345..2c7eb578d 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -427,7 +427,7 @@ to download the full example code</p>
 <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;x&quot;</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#tuple" title="builtins.tuple" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">x</span><span class="o">.</span><span class="n">shape</span></a><span class="p">)</span>
 </pre></div>
 </div>
-<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip3d4ad8e7-770b-40cf-8e7d-98194e176a32 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.zip4f963325-f3ae-4e06-aa8a-0acd95318670 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 8de17e5fa..d3ecc71b7 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -432,13 +432,13 @@ python3 -m pip install -f https://release.oneflow.info <span class="nv">oneflow<
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: &quot;https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip&quot; to /workspace/.oneflow/flowvision_cache/resnet18.zip
 
   0%|          | 0.00/41.5M [00:00&lt;?, ?B/s]
- 15%|#5        | 6.40M/41.5M [00:00&lt;00:00, 67.1MB/s]
- 31%|###       | 12.8M/41.5M [00:00&lt;00:00, 50.4MB/s]
- 43%|####3     | 17.8M/41.5M [00:00&lt;00:00, 40.9MB/s]
- 58%|#####7    | 24.0M/41.5M [00:00&lt;00:00, 38.4MB/s]
- 77%|#######7  | 32.0M/41.5M [00:00&lt;00:00, 45.5MB/s]
- 92%|#########2| 38.3M/41.5M [00:00&lt;00:00, 46.5MB/s]
-100%|##########| 41.5M/41.5M [00:00&lt;00:00, 45.9MB/s]
+ 19%|#9        | 7.99M/41.5M [00:00&lt;00:00, 45.1MB/s]
+ 35%|###4      | 14.3M/41.5M [00:00&lt;00:00, 42.6MB/s]
+ 54%|#####3    | 22.4M/41.5M [00:00&lt;00:00, 55.8MB/s]
+ 68%|######7   | 28.2M/41.5M [00:00&lt;00:00, 45.3MB/s]
+ 85%|########4 | 35.2M/41.5M [00:00&lt;00:00, 52.9MB/s]
+ 98%|#########8| 40.8M/41.5M [00:00&lt;00:00, 52.8MB/s]
+100%|##########| 41.5M/41.5M [00:00&lt;00:00, 51.2MB/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 06beecbf1..753870e60 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -414,9 +414,9 @@ be unstable.</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: &quot;https://download.pytorch.org/models/resnet18-f37072fd.pth&quot; to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
 
   0%|          | 0.00/44.7M [00:00&lt;?, ?B/s]
- 27%|##7       | 12.2M/44.7M [00:00&lt;00:00, 128MB/s]
- 55%|#####4    | 24.5M/44.7M [00:00&lt;00:00, 128MB/s]
-100%|##########| 44.7M/44.7M [00:00&lt;00:00, 157MB/s]
+ 40%|###9      | 17.8M/44.7M [00:00&lt;00:00, 186MB/s]
+ 92%|#########1| 40.9M/44.7M [00:00&lt;00:00, 219MB/s]
+100%|##########| 44.7M/44.7M [00:00&lt;00:00, 217MB/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 4acfdf2d6..9d75a13f0 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -636,7 +636,7 @@ banana (score = 0.00022)
 desk (score = 0.00019)
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  1.640 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  0.652 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 f07188597..c8d4315a9 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -327,7 +327,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>04:59.280</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>04:54.266</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 81%" />
@@ -335,44 +335,44 @@
 <col style="width: 8%" />
 </colgroup>
 <tbody>
-<tr class="row-odd"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:01.640</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
+<td><p>01:01.268</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>01:01.434</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
+<td><p>01:00.652</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>00:39.159</p></td>
+<td><p>00:38.297</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>00:28.325</p></td>
+<td><p>00:26.831</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>00:25.406</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
+<td><p>00:24.406</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
-<tr class="row-even"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
-<td><p>00:24.615</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
+<td><p>00:24.192</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
-<td><p>00:21.857</p></td>
+<td><p>00:22.034</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></td>
-<td><p>00:19.681</p></td>
+<td><p>00:19.498</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>00:14.774</p></td>
+<td><p>00:14.765</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>00:02.389</p></td>
+<td><p>00:02.323</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 </tbody>
diff --git a/docs/how_to/deploy_models/deploy_model_on_android.html b/docs/how_to/deploy_models/deploy_model_on_android.html
index ac6d3d9d0..64070417a 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -653,7 +653,7 @@ to the remote android device.</p>
 Evaluate inference time cost...
 Execution time summary:
  mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)
-  16.3602      16.3169      17.0110      15.8769       0.3716
+  14.6335      14.5762      15.0906      14.3597       0.2344
 </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 b80cf17eb..7713de322 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -436,15 +436,15 @@ be unstable.</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: &quot;https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth&quot; to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
 
   0%|          | 0.00/170M [00:00&lt;?, ?B/s]
-  5%|5         | 8.53M/170M [00:00&lt;00:01, 89.3MB/s]
- 13%|#3        | 22.3M/170M [00:00&lt;00:01, 122MB/s]
- 26%|##6       | 44.9M/170M [00:00&lt;00:00, 174MB/s]
- 40%|####      | 68.2M/170M [00:00&lt;00:00, 202MB/s]
- 54%|#####3    | 91.7M/170M [00:00&lt;00:00, 218MB/s]
- 67%|######7   | 114M/170M [00:00&lt;00:00, 224MB/s]
- 82%|########2 | 140M/170M [00:00&lt;00:00, 239MB/s]
- 96%|#########5| 163M/170M [00:00&lt;00:00, 240MB/s]
-100%|##########| 170M/170M [00:00&lt;00:00, 216MB/s]
+  9%|9         | 15.9M/170M [00:00&lt;00:00, 166MB/s]
+ 19%|#9        | 32.7M/170M [00:00&lt;00:00, 171MB/s]
+ 30%|###       | 51.1M/170M [00:00&lt;00:00, 181MB/s]
+ 43%|####3     | 73.6M/170M [00:00&lt;00:00, 201MB/s]
+ 56%|#####5    | 94.3M/170M [00:00&lt;00:00, 207MB/s]
+ 68%|######7   | 115M/170M [00:00&lt;00:00, 209MB/s]
+ 82%|########2 | 139M/170M [00:00&lt;00:00, 225MB/s]
+ 96%|#########6| 163M/170M [00:00&lt;00:00, 233MB/s]
+100%|##########| 170M/170M [00:00&lt;00:00, 215MB/s]
 /usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
   for i in range(dim)
 /usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the &#39;trunc&#39; function NOT &#39;floor&#39;). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode=&#39;trunc&#39;), or for actual floor division, use torch.div(a, b, rounding_mode=&#39;floor&#39;).
@@ -539,7 +539,7 @@ torchvision rcnn models.</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes  56.936 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes  52.291 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 fb0bd98b4..e64a255d4 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -480,7 +480,9 @@ training. Other models require a full post training calibration.</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: &quot;https://download.pytorch.org/models/mobilenet_v2-b0353104.pth&quot; to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
 
   0%|          | 0.00/13.6M [00:00&lt;?, ?B/s]
-100%|##########| 13.6M/13.6M [00:00&lt;00:00, 183MB/s]
+ 21%|##        | 2.84M/13.6M [00:00&lt;00:00, 29.8MB/s]
+ 48%|####8     | 6.55M/13.6M [00:00&lt;00:00, 35.1MB/s]
+100%|##########| 13.6M/13.6M [00:00&lt;00:00, 60.0MB/s]
 </pre></div>
 </div>
 </div>
@@ -569,7 +571,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
  mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)
-  90.2168      90.1767      91.6216      90.0417       0.1971
+  88.5563      88.5150      91.6298      88.1754       0.3598
 </pre></div>
 </div>
 <div class="admonition note">
@@ -608,7 +610,7 @@ This includes support for the VNNI 8 bit dot product instruction (CascadeLake or
 <div class="section" id="deploy-a-quantized-tflite-model">
 <h2>Deploy a quantized TFLite Model<a class="headerlink" href="#deploy-a-quantized-tflite-model" title="Permalink to this headline">¶</a></h2>
 <p>TODO</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  8.416 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  7.976 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 644343ef6..ca68be629 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -573,7 +573,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
  mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)
-  119.8795     119.8115     123.2919     119.0556      0.4566
+  118.6259     118.6307     121.9512     117.6234      0.4937
 </pre></div>
 </div>
 <div class="admonition note">
@@ -601,7 +601,7 @@ network for ARM CPU</span></a>.</p></li>
 </ul>
 </div></blockquote>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  55.736 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  56.238 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 d3f1ad4d0..226f76b38 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -509,7 +509,7 @@ for calibration. But the accuracy might be impacted.</p>
   DeprecationWarning,
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  31.595 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  25.594 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 fa3b1f842..b0adba3fc 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -441,23 +441,22 @@ to your device.</p>
 Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
 
   0%|          | 0/132723 [00:00&lt;?, ?KB/s]
-  4%|4         | 5876/132723 [00:00&lt;00:02, 58755.15KB/s]
- 11%|#         | 14224/132723 [00:00&lt;00:01, 73293.49KB/s]
- 16%|#6        | 21554/132723 [00:00&lt;00:01, 66847.48KB/s]
- 23%|##2       | 30116/132723 [00:00&lt;00:01, 73846.90KB/s]
- 29%|##9       | 38702/132723 [00:00&lt;00:01, 78021.68KB/s]
- 36%|###5      | 47300/132723 [00:00&lt;00:01, 80660.45KB/s]
- 42%|####2     | 55876/132723 [00:00&lt;00:00, 82299.23KB/s]
- 49%|####8     | 64424/132723 [00:00&lt;00:00, 83297.50KB/s]
- 55%|#####5    | 73065/132723 [00:00&lt;00:00, 84261.62KB/s]
- 62%|######1   | 81695/132723 [00:01&lt;00:00, 84885.24KB/s]
- 68%|######7   | 90197/132723 [00:01&lt;00:00, 83731.71KB/s]
- 74%|#######4  | 98583/132723 [00:01&lt;00:00, 76340.67KB/s]
- 81%|########  | 107119/132723 [00:01&lt;00:00, 78873.92KB/s]
- 87%|########6 | 115115/132723 [00:01&lt;00:00, 71527.77KB/s]
- 93%|#########3| 123700/132723 [00:01&lt;00:00, 75392.18KB/s]
-100%|#########9| 132307/132723 [00:01&lt;00:00, 78361.48KB/s]
-100%|##########| 132723/132723 [00:01&lt;00:00, 77934.12KB/s]
+  4%|4         | 5951/132723 [00:00&lt;00:02, 59505.52KB/s]
+ 11%|#         | 14482/132723 [00:00&lt;00:01, 74681.89KB/s]
+ 17%|#6        | 21951/132723 [00:00&lt;00:01, 73710.82KB/s]
+ 23%|##2       | 30523/132723 [00:00&lt;00:01, 78412.00KB/s]
+ 29%|##9       | 39113/132723 [00:00&lt;00:01, 81096.28KB/s]
+ 36%|###5      | 47760/132723 [00:00&lt;00:01, 82912.94KB/s]
+ 42%|####2     | 56376/132723 [00:00&lt;00:00, 83970.79KB/s]
+ 49%|####8     | 64985/132723 [00:00&lt;00:00, 84639.90KB/s]
+ 55%|#####5    | 73564/132723 [00:00&lt;00:00, 84996.59KB/s]
+ 62%|######1   | 82111/132723 [00:01&lt;00:00, 85137.95KB/s]
+ 68%|######8   | 90709/132723 [00:01&lt;00:00, 85392.48KB/s]
+ 75%|#######4  | 99347/132723 [00:01&lt;00:00, 85689.31KB/s]
+ 81%|########1 | 107935/132723 [00:01&lt;00:00, 85739.78KB/s]
+ 88%|########7 | 116510/132723 [00:01&lt;00:00, 60780.04KB/s]
+ 94%|#########4| 125130/132723 [00:01&lt;00:00, 66730.83KB/s]
+100%|##########| 132723/132723 [00:01&lt;00:00, 76760.78KB/s]
 </pre></div>
 </div>
 <p>Create TVM runtime and do inference
@@ -500,7 +499,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
 <span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
 </pre></div>
 </div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes  33.784 seconds)</p>
+<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes  31.487 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 18af59f6e..2b30a13c1 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -327,7 +327,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>11:20.023</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>11:06.648</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 86%" />
@@ -336,35 +336,35 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>02:56.936</p></td>
+<td><p>02:52.291</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>02:33.784</p></td>
+<td><p>02:31.487</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>01:55.736</p></td>
+<td><p>01:56.238</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>01:31.595</p></td>
+<td><p>01:25.594</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized.html#sphx-glr-how-to-deploy-models-deploy-prequantized-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized.py</span></code>)</p></td>
-<td><p>01:08.416</p></td>
+<td><p>01:07.976</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:29.592</p></td>
+<td><p>00:28.682</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_nano.html#sphx-glr-how-to-deploy-models-deploy-model-on-nano-py"><span class="std std-ref">Deploy the Pretrained Model on Jetson Nano</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_nano.py</span></code>)</p></td>
-<td><p>00:22.186</p></td>
+<td><p>00:22.375</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:21.771</p></td>
+<td><p>00:21.999</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index aa69dbcfd..084cabbcb 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -612,7 +612,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
 <span class="n">module</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">params</span></a> <span class="o">=</span> <span class="n">get_mobilenet</span><span class="p">()</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip011b7b19-964a-432e-b684-65a117c55c10 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.zip37540545-1feb-45b6-986d-fc172d475297 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>
@@ -676,7 +676,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
   &quot;target_host parameter is going to be deprecated. &quot;
-  Check failed: (lower) is false: Intrinsic lowering function for target llvm, intrinsic name tir.sqrt, type 150 not found
+  Check failed: (lower) is false: FloatImm lowering function for target llvm type 150 not found
 </pre></div>
 </div>
 <p>When we attempt to run the model, we get a familiar error telling us that more functions need to be registered for myfloat.</p>
diff --git a/docs/how_to/extend_tvm/sg_execution_times.html b/docs/how_to/extend_tvm/sg_execution_times.html
index 417376021..3bfb3f629 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -327,7 +327,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:40.616</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:40.613</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 84%" />
@@ -336,11 +336,11 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:37.483</p></td>
+<td><p>00:37.459</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>00:02.195</p></td>
+<td><p>00:02.217</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>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 4f2dc9f95..743cba191 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -512,10 +512,10 @@ profile the execution time of each passes.</p>
 </pre></div>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6635us [6635us] (45.62%; 45.62%)
-FoldScaleAxis: 7911us [6us] (54.38%; 54.38%)
-        FoldConstant: 7904us [1581us] (54.34%; 99.92%)
-                InferType: 6323us [6323us] (43.47%; 80.00%)
+InferType: 6423us [6423us] (45.69%; 45.69%)
+FoldScaleAxis: 7636us [5us] (54.31%; 54.31%)
+        FoldConstant: 7631us [1565us] (54.28%; 99.93%)
+                InferType: 6066us [6066us] (43.15%; 79.50%)
 </pre></div>
 </div>
 </div>
@@ -537,10 +537,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
 </pre></div>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6275us [6275us] (44.81%; 44.81%)
-FoldScaleAxis: 7731us [5us] (55.19%; 55.19%)
-        FoldConstant: 7725us [1613us] (55.16%; 99.93%)
-                InferType: 6112us [6112us] (43.64%; 79.12%)
+InferType: 6142us [6142us] (44.24%; 44.24%)
+FoldScaleAxis: 7740us [6us] (55.76%; 55.76%)
+        FoldConstant: 7734us [1628us] (55.71%; 99.92%)
+                InferType: 6105us [6105us] (43.98%; 78.94%)
 </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 7c76dfec8..763b7615d 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -564,7 +564,7 @@ latency of convolution.</p>
 <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;Convolution: </span><span class="si">%f</span><span class="s2"> ms&quot;</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">*</span> <span cl [...]
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.143435 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.282266 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 a0b24ff69..92db4ef9e 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -906,7 +906,7 @@ be able to run on our build server</p>
     <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms&quot;</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 6.874169 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 8.974075 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 8fbde733a..4764f6e54 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -461,8 +461,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
 <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;Baseline: </span><span class="si">%f</span><span class="s2">&quot;</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018770
-Baseline: 3.443516
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.016981
+Baseline: 3.275948
 </pre></div>
 </div>
 <p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -522,7 +522,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
 <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;Opt1: </span><span class="si">%f</span><span class="s2">&quot;</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.297884
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.296299
 </pre></div>
 </div>
 <p>Here is the generated IR after blocking.</p>
@@ -589,7 +589,7 @@ vastly.</p>
 <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;Opt2: </span><span class="si">%f</span><span class="s2">&quot;</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.332118
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.334851
 </pre></div>
 </div>
 <p>Here is the generated IR after vectorization.</p>
@@ -650,7 +650,7 @@ the access pattern for A matrix is more cache friendly.</p>
 <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;Opt3: </span><span class="si">%f</span><span class="s2">&quot;</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.115934
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.113997
 </pre></div>
 </div>
 <p>Here is the generated IR after loop permutation.</p>
@@ -733,7 +733,7 @@ flattening.</p>
 <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;Opt4: </span><span class="si">%f</span><span class="s2">&quot;</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110889
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109449
 </pre></div>
 </div>
 <p>Here is the generated IR after array packing.</p>
@@ -819,7 +819,7 @@ write to C when all the block results are ready.</p>
 <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;Opt5: </span><span class="si">%f</span><span class="s2">&quot;</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111615
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.103335
 </pre></div>
 </div>
 <p>Here is the generated IR after blocking.</p>
@@ -909,7 +909,7 @@ write to C when all the block results are ready.</p>
 <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;Opt6: </span><span class="si">%f</span><span class="s2">&quot;</span> <span class="o">%</span> <span class="n">opt6_time</span><span class="p">)</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.144957
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.133752
 </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 3a8f20b76..9000b435d 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -327,7 +327,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:34.478</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:32.980</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 83%" />
@@ -336,15 +336,15 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:32.219</p></td>
+<td><p>00:30.819</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>00:01.231</p></td>
+<td><p>00:01.201</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>00:01.029</p></td>
+<td><p>00:00.960</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 aa2600d51..d385f89bd 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -327,7 +327,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>06:05.157</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>06:04.566</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 85%" />
@@ -336,27 +336,27 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></td>
-<td><p>03:19.557</p></td>
+<td><p>03:14.676</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>01:22.001</p></td>
+<td><p>01:22.732</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="tune_network_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></td>
-<td><p>00:46.087</p></td>
+<td><p>00:46.180</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>00:20.142</p></td>
+<td><p>00:23.425</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></td>
-<td><p>00:08.758</p></td>
+<td><p>00:08.883</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></td>
-<td><p>00:08.611</p></td>
+<td><p>00:08.670</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 b71611ba6..9cb50fa2e 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
@@ -491,413 +491,76 @@ cooperative fetching, unrolling and operator fusion.</p>
              compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
   buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
   preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
-  attr [IterVar(blockIdx.x: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;blockIdx.x&quot;)] &quot;thread_extent&quot; = 32;
-  allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
-  allocate(pad_temp.shared: Pointer(shared float32), float32, [504]), storage_scope = shared;
-  allocate(kernel.shared: Pointer(shared float32), float32, [384]), storage_scope = shared;
+  attr [IterVar(blockIdx.x: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;blockIdx.x&quot;)] &quot;thread_extent&quot; = 112;
+  allocate(conv2d_nchw: Pointer(local float32), float32, [4]), storage_scope = local;
+  allocate(pad_temp.shared: Pointer(shared float32), float32, [54]), storage_scope = shared;
+  allocate(kernel.shared: Pointer(shared float32), float32, [576]), 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, [4], [], scope=&quot;local&quot;, align=8)[0] = 0f32
-    conv2d_nchw_1[2] = 0f32
-    conv2d_nchw_1[4] = 0f32
-    conv2d_nchw_1[6] = 0f32
-    conv2d_nchw_1[8] = 0f32
-    conv2d_nchw_1[10] = 0f32
-    conv2d_nchw_1[12] = 0f32
+    conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope=&quot;local&quot;, align=16)[0] = 0f32
     conv2d_nchw_1[1] = 0f32
+    conv2d_nchw_1[2] = 0f32
     conv2d_nchw_1[3] = 0f32
-    conv2d_nchw_1[5] = 0f32
-    conv2d_nchw_1[7] = 0f32
-    conv2d_nchw_1[9] = 0f32
-    conv2d_nchw_1[11] = 0f32
-    conv2d_nchw_1[13] = 0f32
-    for (rc.outer.outer: int32, 0, 64) {
-      for (ry.outer.outer: int32, 0, 3) {
-        let cse_var_4: int32 = (rc.outer.outer*392)
-        let cse_var_3: int32 = (ry.outer.outer*7)
-        let cse_var_2: int32 = (rc.outer.outer*72)
-        let cse_var_1: int32 = (ry.outer.outer*3)
-         {
-          attr [IterVar(threadIdx.x_1: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
-          pad_temp.shared_1: Buffer(pad_temp.shared, float32, [504], [], scope=&quot;shared&quot;)[threadIdx.x_1] = @tir.if_then_else(((((1 &lt;= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) &amp;&amp; ((floordiv(threadIdx.x_1, 9) + ry.outer.outer) &lt; 8)) &amp;&amp; (1 &lt;= floormod(threadIdx.x_1, 9))) &amp;&amp; (floormod(threadIdx.x_1, 9) &lt; 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
-          attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
-          pad_temp.shared_1[(threadIdx.x_1 + 56)] = @tir.if_then_else(((((1 &lt;= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) &amp;&amp; ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) &lt; 8)) &amp;&amp; (1 &lt;= floormod((threadIdx.x_1 + 2), 9))) &amp;&amp; (floormod((threadIdx.x_1 + 2), 9) &lt; 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 56), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
-          attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
-          pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((1 &lt;= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) &amp;&amp; ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) &lt; 8)) &amp;&amp; (1 &lt;= floormod((threadIdx.x_1 + 4), 9))) &amp;&amp; (floormod((threadIdx.x_1 + 4), 9) &lt; 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 112), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
-          attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
-          pad_temp.shared_1[(threadIdx.x_1 + 168)] = @tir.if_then_else(((((1 &lt;= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) &amp;&amp; ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) &lt; 8)) &amp;&amp; (1 &lt;= floormod((threadIdx.x_1 + 6), 9))) &amp;&amp; (floormod((threadIdx.x_1 + 6), 9) &lt; 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 168), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
-          attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
-          pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((1 &lt;= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) &amp;&amp; ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) &lt; 8)) &amp;&amp; (1 &lt;= floormod((threadIdx.x_1 + 8), 9))) &amp;&amp; (floormod((threadIdx.x_1 + 8), 9) &lt; 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 224), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
-          attr [IterVar(threadIdx.x_1, (nullptr), &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;= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) &amp;&amp; ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) &lt; 8)) &amp;&amp; (1 &lt;= floormod((threadIdx.x_1 + 1), 9))) &amp;&amp; (floormod((threadIdx.x_1 + 1), 9) &lt; 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 280), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
-          attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
-          pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((((1 &lt;= (floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer)) &amp;&amp; ((floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer) &lt; 8)) &amp;&amp; (1 &lt;= floormod((threadIdx.x_1 + 3), 9))) &amp;&amp; (floormod((threadIdx.x_1 + 3), 9) &lt; 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 336), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
-          attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
-          pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((1 &lt;= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) &amp;&amp; ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) &lt; 8)) &amp;&amp; (1 &lt;= floormod((threadIdx.x_1 + 5), 9))) &amp;&amp; (floormod((threadIdx.x_1 + 5), 9) &lt; 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 392), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
-          attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
-          pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((1 &lt;= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) &amp;&amp; ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) &lt; 8)) &amp;&amp; (1 &lt;= floormod((threadIdx.x_1 + 7), 9))) &amp;&amp; (floormod((threadIdx.x_1 + 7), 9) &lt; 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 448), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
-          attr [IterVar(threadIdx.x_2: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
-          kernel.shared_1: Buffer(kernel.shared, float32, [384], [], scope=&quot;shared&quot;)[threadIdx.x_2] = kernel[((((((blockIdx.x*73728) + (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; = 56;
-          kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 56), 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; = 56;
-          kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 112), 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; = 56;
-          kernel.shared_1[(threadIdx.x_2 + 168)] = kernel[(((((((blockIdx.x*73728) + (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)) + 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 + 224)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 224), 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; = 56;
-          kernel.shared_1[(threadIdx.x_2 + 280)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 280), 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; = 56;
-          if @tir.likely((threadIdx.x_2 &lt; 48), dtype=bool) {
-            kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[(((((((blockIdx.x*73728) + (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)) + 64512)]
-          }
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*9)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*48)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*48)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*48)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*48)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*48)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*48)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*48)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 24)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 24)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 24)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 24)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 24)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 24)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 24)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 1)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 1)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 1)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 1)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 1)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 1)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 1)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 25)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 25)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 25)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 25)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 25)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 25)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 25)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 2)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 2)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 2)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 2)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 2)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 2)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 8)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 2)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 26)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 26)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 26)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 26)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 26)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 26)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 8)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 26)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 3)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 3)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 3)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 66)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 3)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 67)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 3)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 68)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 3)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 69)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 3)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 27)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 27)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 27)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 66)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 27)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 67)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 27)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 68)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 27)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 69)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 27)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 4)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 4)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 66)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 4)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 67)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 4)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 68)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 4)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 69)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 4)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 70)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 4)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 28)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 28)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 66)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 28)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 67)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 28)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 68)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 28)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 69)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 28)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 70)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 28)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 5)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 66)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 5)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 67)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 5)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 68)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 5)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 69)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 5)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 70)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 5)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 71)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 5)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 29)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 66)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 29)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 67)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 29)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 68)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 29)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 69)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 29)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 70)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 29)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 71)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 29)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 6)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 6)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 6)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 129)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 6)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 130)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 6)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 131)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 6)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 132)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 6)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 30)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 30)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 30)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 129)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 30)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 130)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 30)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 131)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 30)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 132)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 30)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 7)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 7)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 129)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 7)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 130)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 7)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 131)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 7)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 132)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 7)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 133)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 7)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 31)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 31)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 129)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 31)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 130)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 31)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 131)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 31)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 132)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 31)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 133)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 31)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 8)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 129)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 8)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 130)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 8)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 131)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 8)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 132)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 8)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 133)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 8)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 134)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 8)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 32)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 129)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 32)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 130)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 32)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 131)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 32)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 132)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 32)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 133)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 32)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 134)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 32)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 9)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 9)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 9)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 192)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 9)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 193)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 9)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 194)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 9)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 195)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 9)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 33)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 33)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 33)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 192)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 33)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 193)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 33)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 194)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 33)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 195)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 33)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 10)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 10)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 192)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 10)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 193)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 10)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 194)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 10)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 195)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 10)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 10)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 34)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 34)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 192)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 34)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 193)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 34)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 194)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 34)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 195)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 34)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 34)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 11)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 192)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 11)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 193)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 11)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 194)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 11)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 195)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 11)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 11)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 11)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 35)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 192)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 35)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 193)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 35)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 194)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 35)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 195)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 35)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 35)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 35)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 12)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 12)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 12)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 12)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 12)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 12)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 12)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 36)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 36)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 36)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 36)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 36)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 36)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 36)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 13)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 13)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 13)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 13)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 13)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 13)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 13)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 37)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 37)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 37)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 37)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 37)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 37)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 37)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 14)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 14)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 14)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 14)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 14)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 14)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 260)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 14)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 38)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 38)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 38)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 38)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 38)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 38)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 260)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 38)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 315)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 15)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 15)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 15)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 318)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 15)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 319)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 15)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 320)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 15)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 321)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 15)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 315)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 39)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 39)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 39)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 318)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 39)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 319)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 39)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 320)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 39)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 321)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 39)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 16)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 16)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 318)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 16)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 319)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 16)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 320)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 16)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 321)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 16)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 322)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 16)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 40)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 40)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 318)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 40)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 319)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 40)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 320)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 40)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 321)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 40)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 322)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 40)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 17)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 318)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 17)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 319)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 17)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 320)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 17)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 321)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 17)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 322)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 17)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 323)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 17)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 41)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 318)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 41)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 319)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 41)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 320)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 41)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 321)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 41)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 322)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 41)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 323)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 41)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 18)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 18)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 18)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 381)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 18)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 382)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 18)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 383)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 18)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 384)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 18)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 42)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 42)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 42)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 381)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 42)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 382)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 42)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 383)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 42)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 384)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 42)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 19)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 19)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 381)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 19)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 382)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 19)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 383)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 19)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 384)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 19)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 385)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 19)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 43)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 43)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 381)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 43)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 382)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 43)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 383)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 43)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 384)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 43)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 385)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 43)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 20)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 381)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 20)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 382)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 20)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 383)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 20)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 384)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 20)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 385)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 20)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 386)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 20)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 44)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 381)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 44)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 382)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 44)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 383)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 44)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 384)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 44)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 385)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 44)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 386)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 44)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 21)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 21)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 21)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 444)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 21)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 445)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 21)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 446)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 21)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 447)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 21)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 45)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 45)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 45)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 444)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 45)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 445)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 45)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 446)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 45)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 447)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 45)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 22)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 22)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 444)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 22)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 445)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 22)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 446)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 22)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 447)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 22)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 448)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 22)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 46)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 46)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 444)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 46)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 445)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 46)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 446)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 46)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 447)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 46)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 448)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 46)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 23)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 444)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 23)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 445)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 23)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 446)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 23)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 447)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 23)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 448)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 23)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 449)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 23)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 47)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 444)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 47)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 445)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 47)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 446)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 47)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 447)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 47)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 448)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 47)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 449)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 47)]))
+    for (rc.outer.outer: int32, 0, 256) {
+      let cse_var_1: int32 = (rc.outer.outer*18)
+       {
+        attr [IterVar(threadIdx.x_1: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
+        if @tir.likely((threadIdx.x_1 &lt; 54), dtype=bool) {
+          pad_temp.shared_1: Buffer(pad_temp.shared, float32, [54], [], scope=&quot;shared&quot;)[threadIdx.x_1] = @tir.if_then_else(((((1 &lt;= (floordiv(floormod(threadIdx.x_1, 27), 9) + floormod(blockIdx.x, 7))) &amp;&amp; ((floordiv(floormod(threadIdx.x_1, 27), 9) + floormod(blockIdx.x, 7)) &lt; 8)) &amp;&amp; (1 &lt;= floormod(threadIdx.x_1, 9))) &amp;&amp; (floormod(threadIdx.x_1, 9) &lt; 8)), data[((((((rc.outer.outer*98) + (floordiv(threadIdx.x_1, 27)*49)) + (floordiv(floormod(th [...]
+        }
+        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, [576], [], scope=&quot;shared&quot;)[threadIdx.x_2] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 18))]
+        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[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 56), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 18))]
+        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[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 112), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 18))]
+        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[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 168), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 6), 18))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
+        kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 224), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 18))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
+        kernel.shared_1[(threadIdx.x_2 + 280)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 280), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 10), 18))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
+        kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 336), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 12), 18))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
+        kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 392), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 14), 18))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
+        kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 448), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 18))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
+        kernel.shared_1[(threadIdx.x_2 + 504)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 18)) + 129024)]
+        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; 16), dtype=bool) {
+          kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 560), 18)*4608)) + cse_var_1) + (threadIdx.x_2 + 2))]
+        }
+        for (rx.outer.inner: int32, 0, 3) {
+          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(rx.outer.inner + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + rx.outer.inner)]))
+          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(rx.outer.inner + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 18)]))
+          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(rx.outer.inner + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 36)]))
+          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(rx.outer.inner + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 54)]))
+          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 3)]))
+          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 21)]))
+          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 39)]))
+          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 57)]))
+          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 6)]))
+          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 24)]))
+          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 42)]))
+          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 60)]))
+          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 9)]))
+          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 27)]))
+          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 45)]))
+          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 63)]))
+          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 12)]))
+          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 30)]))
+          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 48)]))
+          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 66)]))
+          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 15)]))
+          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 33)]))
+          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 51)]))
+          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rx.outer.inner + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + rx.outer.inner) + 69)]))
         }
       }
     }
-    for (i1.inner: int32, 0, 2) {
-      compute[((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
-      compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 1)] = max((conv2d_nchw_1[(i1.inner + 2)] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
-      compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 2)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
-      compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 3)] = max((conv2d_nchw_1[(i1.inner + 6)] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
-      compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 4)] = max((conv2d_nchw_1[(i1.inner + 8)] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
-      compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 5)] = max((conv2d_nchw_1[(i1.inner + 10)] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
-      compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 6)] = max((conv2d_nchw_1[(i1.inner + 12)] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+    for (i1.inner: int32, 0, 4) {
+      compute[(((((floordiv(blockIdx.x, 7)*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[i1.inner] + bias[(((floordiv(blockIdx.x, 7)*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
     }
   }
 }
@@ -934,7 +597,7 @@ 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: 0.221 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.391 ms
 </pre></div>
 </div>
 </div>
@@ -963,37 +626,37 @@ 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=2)
+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=7)
+conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
 conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
 conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
 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=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_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
+conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
+conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
 conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
-conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
-conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
+conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
+conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
 s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
 compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
 compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
 compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
-compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
+compute_i1_o_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=7)
+compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
 compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
 compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=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=7)
+compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
+compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
 s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
 s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
 kernel_shared = s.cache_read(kernel, &quot;shared&quot;, [conv2d_nchw])
@@ -1019,7 +682,7 @@ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fus
 s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
 pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
 s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis(&quot;threadIdx.x&quot;))
-s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, &quot;auto_unroll_max_step&quot;, 1024)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, &quot;auto_unroll_max_step&quot;, 64)
 s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, &quot;unroll_explicit&quot;, True)
 
 CUDA source code:
@@ -1038,391 +701,61 @@ CUDA source code:
   #define uint64_t unsigned long long
 #endif
 extern &quot;C&quot; __global__ void __launch_bounds__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
-  float conv2d_nchw[14];
-  __shared__ float pad_temp_shared[504];
-  __shared__ float kernel_shared[384];
+  float conv2d_nchw[4];
+  __shared__ float pad_temp_shared[54];
+  __shared__ float kernel_shared[576];
   conv2d_nchw[0] = 0.000000e+00f;
-  conv2d_nchw[2] = 0.000000e+00f;
-  conv2d_nchw[4] = 0.000000e+00f;
-  conv2d_nchw[6] = 0.000000e+00f;
-  conv2d_nchw[8] = 0.000000e+00f;
-  conv2d_nchw[10] = 0.000000e+00f;
-  conv2d_nchw[12] = 0.000000e+00f;
   conv2d_nchw[1] = 0.000000e+00f;
+  conv2d_nchw[2] = 0.000000e+00f;
   conv2d_nchw[3] = 0.000000e+00f;
-  conv2d_nchw[5] = 0.000000e+00f;
-  conv2d_nchw[7] = 0.000000e+00f;
-  conv2d_nchw[9] = 0.000000e+00f;
-  conv2d_nchw[11] = 0.000000e+00f;
-  conv2d_nchw[13] = 0.000000e+00f;
-  for (int rc_outer_outer = 0; rc_outer_outer &lt; 64; ++rc_outer_outer) {
-    for (int ry_outer_outer = 0; ry_outer_outer &lt; 3; ++ry_outer_outer) {
-      __syncthreads();
-      pad_temp_shared[((int)threadIdx.x)] = (((((1 &lt;= ((((int)threadIdx.x) / 9) + ry_outer_outer)) &amp;&amp; (((((int)threadIdx.x) / 9) + ry_outer_outer) &lt; 8)) &amp;&amp; (1 &lt;= (((int)threadIdx.x) % 9))) &amp;&amp; ((((int)threadIdx.x) % 9) &lt; 8)) ? data[(((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
-      pad_temp_shared[(((int)threadIdx.x) + 56)] = (((((1 &lt;= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) &amp;&amp; (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) &lt; 8)) &amp;&amp; (1 &lt;= ((((int)threadIdx.x) + 2) % 9))) &amp;&amp; (((((int)threadIdx.x) + 2) % 9) &lt; 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 56) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
-      pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((1 &lt;= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) &amp;&amp; (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) &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) + 112) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
-      pad_temp_shared[(((int)threadIdx.x) + 168)] = (((((1 &lt;= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) &amp;&amp; (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) &lt; 8)) &amp;&amp; (1 &lt;= ((((int)threadIdx.x) + 6) % 9))) &amp;&amp; (((((int)threadIdx.x) + 6) % 9) &lt; 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 168) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
-      pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((1 &lt;= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) &amp;&amp; (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) &lt; 8)) &amp;&amp; (1 &lt;= ((((int)threadIdx.x) + 8) % 9))) &amp;&amp; (((((int)threadIdx.x) + 8) % 9) &lt; 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
-      pad_temp_shared[(((int)threadIdx.x) + 280)] = (((((1 &lt;= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) &amp;&amp; (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) &lt; 8)) &amp;&amp; (1 &lt;= ((((int)threadIdx.x) + 1) % 9))) &amp;&amp; (((((int)threadIdx.x) + 1) % 9) &lt; 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 280) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
-      pad_temp_shared[(((int)threadIdx.x) + 336)] = (((((1 &lt;= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) &amp;&amp; (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) &lt; 8)) &amp;&amp; (1 &lt;= ((((int)threadIdx.x) + 3) % 9))) &amp;&amp; (((((int)threadIdx.x) + 3) % 9) &lt; 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 336) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
-      pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((1 &lt;= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) &amp;&amp; (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) &lt; 8)) &amp;&amp; (1 &lt;= ((((int)threadIdx.x) + 5) % 9))) &amp;&amp; (((((int)threadIdx.x) + 5) % 9) &lt; 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 392) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
-      pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((1 &lt;= (((((int)threadIdx.x) + 7) / 9) + ry_outer_outer)) &amp;&amp; ((((((int)threadIdx.x) + 7) / 9) + ry_outer_outer) &lt; 8)) &amp;&amp; (1 &lt;= ((((int)threadIdx.x) + 7) % 9))) &amp;&amp; (((((int)threadIdx.x) + 7) % 9) &lt; 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 448) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
-      kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((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) + 56)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) / 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) + 112)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 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) + 168)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 32256)];
-      kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 224) / 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) + 280)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      if (((int)threadIdx.x) &lt; 48) {
-        kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 64512)];
-      }
-      __syncthreads();
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 9)] * kernel_shared[((((int)threadIdx.x) / 7) * 48)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[((((int)threadIdx.x) / 7) * 48)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[((((int)threadIdx.x) / 7) * 48)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[((((int)threadIdx.x) / 7) * 48)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[((((int)threadIdx.x) / 7) * 48)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[((((int)threadIdx.x) / 7) * 48)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[((((int)threadIdx.x) / 7) * 48)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 24)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 24)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 24)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 24)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 24)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 24)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 24)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 1)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 1)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 1)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 1)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 1)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 1)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 1)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 25)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 25)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 25)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 25)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 25)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 25)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 25)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 2)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 2)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 2)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 2)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 2)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 2)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 8)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 2)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 26)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 26)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 26)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 26)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 26)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 26)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 8)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 26)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 3)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 3)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 3)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 66)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 3)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 67)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 3)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 68)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 3)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 69)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 3)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 27)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 27)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 27)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 66)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 27)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 67)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 27)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 68)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 27)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 69)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 27)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 4)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 4)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 66)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 4)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 67)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 4)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 68)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 4)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 69)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 4)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 70)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 4)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 28)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 28)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 66)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 28)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 67)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 28)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 68)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 28)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 69)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 28)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 70)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 28)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 5)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 66)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 5)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 67)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 5)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 68)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 5)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 69)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 5)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 70)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 5)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 71)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 5)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 29)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 66)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 29)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 67)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 29)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 68)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 29)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 69)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 29)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 70)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 29)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 71)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 29)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 6)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 6)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 6)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 129)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 6)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 130)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 6)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 131)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 6)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 132)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 6)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 30)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 30)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 30)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 129)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 30)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 130)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 30)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 131)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 30)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 132)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 30)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 7)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 7)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 129)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 7)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 130)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 7)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 131)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 7)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 132)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 7)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 133)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 7)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 31)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 31)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 129)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 31)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 130)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 31)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 131)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 31)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 132)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 31)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 133)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 31)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 8)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 129)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 8)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 130)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 8)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 131)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 8)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 132)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 8)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 133)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 8)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 134)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 8)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 32)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 129)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 32)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 130)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 32)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 131)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 32)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 132)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 32)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 133)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 32)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 134)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 32)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 9)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 9)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 9)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 192)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 9)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 193)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 9)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 194)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 9)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 195)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 9)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 33)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 33)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 33)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 192)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 33)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 193)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 33)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 194)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 33)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 195)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 33)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 10)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 10)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 192)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 10)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 193)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 10)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 194)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 10)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 195)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 10)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 10)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 34)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 34)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 192)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 34)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 193)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 34)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 194)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 34)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 195)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 34)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 34)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 11)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 192)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 11)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 193)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 11)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 194)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 11)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 195)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 11)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 11)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 11)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 35)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 192)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 35)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 193)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 35)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 194)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 35)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 195)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 35)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 35)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 35)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 12)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 12)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 12)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 12)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 12)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 12)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 12)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 36)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 36)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 36)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 36)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 36)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 36)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 36)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 13)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 13)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 13)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 13)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 13)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 13)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 13)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 37)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 37)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 37)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 37)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 37)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 37)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 37)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 14)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 14)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 14)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 14)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 14)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 14)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 260)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 14)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 38)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 38)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 38)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 38)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 38)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 38)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 260)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 38)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 315)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 15)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 15)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 15)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 318)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 15)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 319)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 15)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 320)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 15)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 321)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 15)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 315)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 39)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 39)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 39)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 318)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 39)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 319)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 39)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 320)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 39)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 321)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 39)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 16)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 16)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 318)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 16)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 319)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 16)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 320)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 16)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 321)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 16)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 322)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 16)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 40)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 40)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 318)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 40)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 319)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 40)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 320)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 40)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 321)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 40)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 322)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 40)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 17)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 318)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 17)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 319)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 17)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 320)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 17)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 321)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 17)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 322)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 17)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 323)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 17)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 41)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 318)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 41)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 319)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 41)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 320)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 41)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 321)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 41)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 322)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 41)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 323)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 41)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 378)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 18)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 18)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 18)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 381)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 18)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 382)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 18)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 383)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 18)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 384)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 18)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 378)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 42)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 42)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 42)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 381)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 42)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 382)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 42)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 383)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 42)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 384)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 42)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 19)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 19)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 381)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 19)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 382)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 19)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 383)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 19)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 384)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 19)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 385)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 19)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 43)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 43)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 381)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 43)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 382)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 43)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 383)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 43)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 384)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 43)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 385)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 43)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 20)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 381)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 20)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 382)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 20)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 383)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 20)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 384)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 20)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 385)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 20)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 386)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 20)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 44)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 381)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 44)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 382)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 44)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 383)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 44)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 384)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 44)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 385)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 44)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 386)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 44)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 441)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 21)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 21)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 21)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 444)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 21)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 445)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 21)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 446)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 21)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 447)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 21)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 441)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 45)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 45)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 45)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 444)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 45)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 445)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 45)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 446)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 45)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 447)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 45)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 22)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 22)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 444)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 22)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 445)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 22)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 446)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 22)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 447)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 22)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 448)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 22)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 46)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 46)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 444)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 46)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 445)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 46)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 446)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 46)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 447)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 46)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 448)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 46)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 23)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 444)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 23)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 445)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 23)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 446)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 23)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 447)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 23)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 448)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 23)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 449)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 23)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 47)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 444)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 47)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 445)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 47)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 446)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 47)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 447)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 47)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 448)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 47)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 449)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 47)]));
+  for (int rc_outer_outer = 0; rc_outer_outer &lt; 256; ++rc_outer_outer) {
+    __syncthreads();
+    if (((int)threadIdx.x) &lt; 54) {
+      pad_temp_shared[((int)threadIdx.x)] = (((((1 &lt;= (((((int)threadIdx.x) % 27) / 9) + (((int)blockIdx.x) % 7))) &amp;&amp; ((((((int)threadIdx.x) % 27) / 9) + (((int)blockIdx.x) % 7)) &lt; 8)) &amp;&amp; (1 &lt;= (((int)threadIdx.x) % 9))) &amp;&amp; ((((int)threadIdx.x) % 9) &lt; 8)) ? data[((((((rc_outer_outer * 98) + ((((int)threadIdx.x) / 27) * 49)) + (((((int)threadIdx.x) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+    }
+    kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 18)) + (((int)threadIdx.x) % 18))];
+    kernel_shared[(((int)threadIdx.x) + 56)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 56) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 2) % 18))];
+    kernel_shared[(((int)threadIdx.x) + 112)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 4) % 18))];
+    kernel_shared[(((int)threadIdx.x) + 168)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 168) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 6) % 18))];
+    kernel_shared[(((int)threadIdx.x) + 224)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 8) % 18))];
+    kernel_shared[(((int)threadIdx.x) + 280)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 280) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 10) % 18))];
+    kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 336) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 12) % 18))];
+    kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 392) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 14) % 18))];
+    kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 16) % 18))];
+    kernel_shared[(((int)threadIdx.x) + 504)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 18)) + (((int)threadIdx.x) % 18)) + 129024)];
+    if (((int)threadIdx.x) &lt; 16) {
+      kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 560) / 18) * 4608)) + (rc_outer_outer * 18)) + ((int)threadIdx.x)) + 2)];
+    }
+    __syncthreads();
+    for (int rx_outer_inner = 0; rx_outer_inner &lt; 3; ++rx_outer_inner) {
+      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(rx_outer_inner + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + rx_outer_inner)]));
+      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(rx_outer_inner + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 18)]));
+      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(rx_outer_inner + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 36)]));
+      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(rx_outer_inner + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 54)]));
+      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 3)]));
+      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 21)]));
+      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 39)]));
+      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 57)]));
+      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 6)]));
+      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 24)]));
+      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 42)]));
+      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 60)]));
+      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 9)]));
+      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 27)]));
+      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 45)]));
+      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 63)]));
+      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 12)]));
+      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 30)]));
+      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 48)]));
+      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 66)]));
+      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 15)]));
+      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 33)]));
+      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 51)]));
+      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + rx_outer_inner) + 69)]));
     }
   }
-  for (int i1_inner = 0; i1_inner &lt; 2; ++i1_inner) {
-    compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
-    compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 1)] = max((conv2d_nchw[(i1_inner + 2)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
-    compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 2)] = max((conv2d_nchw[(i1_inner + 4)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
-    compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 3)] = max((conv2d_nchw[(i1_inner + 6)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
-    compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 4)] = max((conv2d_nchw[(i1_inner + 8)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
-    compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 5)] = max((conv2d_nchw[(i1_inner + 10)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
-    compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 6)] = max((conv2d_nchw[(i1_inner + 12)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+  for (int i1_inner = 0; i1_inner &lt; 4; ++i1_inner) {
+    compute[((((((((int)blockIdx.x) / 7) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i1_inner] + bias[((((((int)blockIdx.x) / 7) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
   }
 }
 </pre></div>
@@ -1459,7 +792,7 @@ In the example below we resume the status and do more 5 trials.</p>
 Get devices for measurement successfully!
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  19.557 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  14.676 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 5caee5026..12a0ec948 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -906,7 +906,7 @@ so we can read the log file and load the best schedules.</p>
 Evaluate inference time cost...
 Execution time summary:
  mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)
-   9.7572       9.7757       9.8059       9.6899       0.0492
+  10.0790      10.1018      10.1067      10.0283       0.0359
 </pre></div>
 </div>
 </div>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
index 62acf7755..650dcf920 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -925,7 +925,7 @@ so we can read the log file and load the best schedules.</p>
 Evaluate inference time cost...
 Execution time summary:
  mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)
-  760.1820     760.4577     760.7874     759.3009      0.6374
+  753.3373     753.6253     753.7449     752.6417      0.4943
 </pre></div>
 </div>
 </div>
@@ -947,7 +947,7 @@ to learn how to use the RPC Tracker and RPC Server.
 To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
 with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
 </ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  22.001 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  22.732 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 76f77c5b1..523d1693d 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -625,31 +625,103 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
              placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
              compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
   buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
-  preflattened_buffer_map = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_8: placeholder_15: Buffer(placeholder_13, int32, [33], []), placeholder_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_5: placeholder_17: Buffer(placeholder_10, float32, [128, 256], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], [])} {
+  preflattened_buffer_map = {placeholder_8: placeholder_15: Buffer(placeholder_13, int32, [33], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
   for (i0.outer.i1.outer.fused: int32, 0, 32) &quot;parallel&quot; {
     allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global {
-      for (i.outer.inner: int32, 0, 32) {
-        for (i.inner.init: int32, 0, 4) {
-          for (j.init: int32, 0, 16) {
-            compute_5: Buffer(compute_4, float32, [2048], [])[(((i.outer.inner*64) + (i.inner.init*16)) + j.init)] = 0f32
+      for (i.outer.inner: int32, 0, 4) {
+        for (i.inner.init: int32, 0, 32) {
+          let cse_var_1: int32 = ((i.outer.inner*512) + (i.inner.init*16))
+           {
+            compute_5: Buffer(compute_4, float32, [2048], [])[cse_var_1] = 0f32
+            compute_5[(cse_var_1 + 1)] = 0f32
+            compute_5[(cse_var_1 + 2)] = 0f32
+            compute_5[(cse_var_1 + 3)] = 0f32
+            compute_5[(cse_var_1 + 4)] = 0f32
+            compute_5[(cse_var_1 + 5)] = 0f32
+            compute_5[(cse_var_1 + 6)] = 0f32
+            compute_5[(cse_var_1 + 7)] = 0f32
+            compute_5[(cse_var_1 + 8)] = 0f32
+            compute_5[(cse_var_1 + 9)] = 0f32
+            compute_5[(cse_var_1 + 10)] = 0f32
+            compute_5[(cse_var_1 + 11)] = 0f32
+            compute_5[(cse_var_1 + 12)] = 0f32
+            compute_5[(cse_var_1 + 13)] = 0f32
+            compute_5[(cse_var_1 + 14)] = 0f32
+            compute_5[(cse_var_1 + 15)] = 0f32
           }
         }
         for (elem_idx: int32, 0, (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])) {
-          for (i.inner: int32, 0, 4) {
-            for (j: int32, 0, 16) {
-              if @tir.likely((elem_idx &lt; (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
-                let cse_var_1: int32 = (((i.outer.inner*64) + (i.inner*16)) + j)
-                compute_5[cse_var_1] = (compute_5[cse_var_1] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + j)]*max(placeholder[(((i.outer.inner*1024) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
-              }
+          for (i.inner: int32, 0, 32) {
+            if @tir.likely((elem_idx &lt; (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+              let cse_var_2: int32 = ((i.outer.inner*512) + (i.inner*16))
+              compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16))]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+            }
+            if @tir.likely((elem_idx &lt; (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+              let cse_var_3: int32 = (((i.outer.inner*512) + (i.inner*16)) + 1)
+              compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+            }
+            if @tir.likely((elem_idx &lt; (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+              let cse_var_4: int32 = (((i.outer.inner*512) + (i.inner*16)) + 2)
+              compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+            }
+            if @tir.likely((elem_idx &lt; (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+              let cse_var_5: int32 = (((i.outer.inner*512) + (i.inner*16)) + 3)
+              compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+            }
+            if @tir.likely((elem_idx &lt; (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+              let cse_var_6: int32 = (((i.outer.inner*512) + (i.inner*16)) + 4)
+              compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+            }
+            if @tir.likely((elem_idx &lt; (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+              let cse_var_7: int32 = (((i.outer.inner*512) + (i.inner*16)) + 5)
+              compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+            }
+            if @tir.likely((elem_idx &lt; (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+              let cse_var_8: int32 = (((i.outer.inner*512) + (i.inner*16)) + 6)
+              compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+            }
+            if @tir.likely((elem_idx &lt; (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+              let cse_var_9: int32 = (((i.outer.inner*512) + (i.inner*16)) + 7)
+              compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+            }
+            if @tir.likely((elem_idx &lt; (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+              let cse_var_10: int32 = (((i.outer.inner*512) + (i.inner*16)) + 8)
+              compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+            }
+            if @tir.likely((elem_idx &lt; (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+              let cse_var_11: int32 = (((i.outer.inner*512) + (i.inner*16)) + 9)
+              compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+            }
+            if @tir.likely((elem_idx &lt; (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+              let cse_var_12: int32 = (((i.outer.inner*512) + (i.inner*16)) + 10)
+              compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+            }
+            if @tir.likely((elem_idx &lt; (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+              let cse_var_13: int32 = (((i.outer.inner*512) + (i.inner*16)) + 11)
+              compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+            }
+            if @tir.likely((elem_idx &lt; (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+              let cse_var_14: int32 = (((i.outer.inner*512) + (i.inner*16)) + 12)
+              compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+            }
+            if @tir.likely((elem_idx &lt; (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+              let cse_var_15: int32 = (((i.outer.inner*512) + (i.inner*16)) + 13)
+              compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+            }
+            if @tir.likely((elem_idx &lt; (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+              let cse_var_16: int32 = (((i.outer.inner*512) + (i.inner*16)) + 14)
+              compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+            }
+            if @tir.likely((elem_idx &lt; (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+              let cse_var_17: int32 = (((i.outer.inner*512) + (i.inner*16)) + 15)
+              compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
             }
           }
         }
       }
       for (i0.inner: int32, 0, 128) {
-        for (i1.inner: int32, 0, 16) {
-          let cse_var_2: int32 = (((i0.inner*512) + (i0.outer.i1.outer.fused*16)) + i1.inner)
-          compute[cse_var_2] = max((compute_5[((i0.inner*16) + i1.inner)] + placeholder_4[cse_var_2]), 0f32)
-        }
+        let cse_var_18: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*16))
+        compute[ramp(cse_var_18, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_18, 1, 16)]), broadcast(0f32, 16))
       }
     }
   }
@@ -687,7 +759,7 @@ 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: 1.462 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.790 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 1aa74e1b0..0c7cca309 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -327,7 +327,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:45.293</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:45.147</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 84%" />
@@ -336,11 +336,11 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:45.258</p></td>
+<td><p>00:45.110</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
-<td><p>00:00.020</p></td>
+<td><p>00:00.023</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></td>
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 abff233ac..06a57291d 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -1436,8 +1436,8 @@ No: 8   GFLOPS: 0.00/0.00       result: Traceback (most recent call last):
 TimeoutError
 
         [(&#39;tile_f&#39;, [-1, 2, 1, 64]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 1, 4]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 0)],None,4909501
-No: 9   GFLOPS: 181.47/181.47   result: MeasureResult(costs=(0.001275734888888889,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0310184955596924, timestamp=1659640918.6263578)       [(&#39;tile_f&#39;, [-1, 1, 4, 8]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 2, 2]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 0)],None,5072689
-No: 10  GFLOPS: 0.00/181.47     result: Traceback (most recent call last):
+No: 9   GFLOPS: 219.59/219.59   result: MeasureResult(costs=(0.0010542364275862067,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1123545169830322, timestamp=1659647699.6992056)      [(&#39;tile_f&#39;, [-1, 1, 4, 8]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 2, 2]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 0)],None,5072689
+No: 10  GFLOPS: 0.00/219.59     result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 588, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 540, in _build_func_common
@@ -1560,8 +1560,8 @@ Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 871, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
 tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 4, 4, 8]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 7]), (&#39;tile_rc&#39;, [-1, 64, 2]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 0)],None,5092711
-No: 11  GFLOPS: 261.10/261.10   result: MeasureResult(costs=(0.000886633017699115,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.445702075958252, timestamp=1659640919.2690825)        [(&#39;tile_f&#39;, [-1, 8, 2, 1]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 2, 1]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 0)],None,4264713
-No: 12  GFLOPS: 0.00/261.10     result: Traceback (most recent call last):
+No: 11  GFLOPS: 260.07/260.07   result: MeasureResult(costs=(0.0008901485635359116,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7547366619110107, timestamp=1659647700.6220863)      [(&#39;tile_f&#39;, [-1, 8, 2, 1]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 2, 1]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 0)],None,4264713
+No: 12  GFLOPS: 0.00/260.07     result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 588, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 540, in _build_func_common
@@ -1684,7 +1684,7 @@ Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 871, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
 tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 128, 1, 2]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 1, 256]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 0)],None,183542
-No: 13  GFLOPS: 0.00/261.10     result: Traceback (most recent call last):
+No: 13  GFLOPS: 0.00/260.07     result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 588, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 540, in _build_func_common
@@ -1807,7 +1807,7 @@ Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 871, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
 tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 4, 8, 8]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 1, 64]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 0)],None,2482196
-No: 14  GFLOPS: 0.00/261.10     result: Traceback (most recent call last):
+No: 14  GFLOPS: 0.00/260.07     result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 588, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 540, in _build_func_common
@@ -1930,9 +1930,9 @@ Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 871, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
 tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 64, 1, 4]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 7]), (&#39;tile_rc&#39;, [-1, 4, 2]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 1)],None,10306226
-No: 15  GFLOPS: 5.32/261.10     result: MeasureResult(costs=(0.043493526250000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8619730472564697, timestamp=1659640923.8461597)       [(&#39;tile_f&#39;, [-1, 2, 2, 8]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 4, 8]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 1)],None,5330964
-No: 16  GFLOPS: 3.35/261.10     result: MeasureResult(costs=(0.0691233745,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.541823625564575, timestamp=1659640925.0787606)        [(&#39;tile_f&#39;, [-1, 8, 4, 4]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#39;tile_x&#39;, [-1, 1, 1, 7]), (&#39;tile_rc&#39;, [-1, 4, 1]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 0)],None,2140058
-No: 17  GFLOPS: 0.00/261.10     result: Traceback (most recent call last):
+No: 15  GFLOPS: 5.29/260.07     result: MeasureResult(costs=(0.043795402250000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.839280366897583, timestamp=1659647705.1306255)        [(&#39;tile_f&#39;, [-1, 2, 2, 8]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 4, 8]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 1)],None,5330964
+No: 16  GFLOPS: 3.34/260.07     result: MeasureResult(costs=(0.06939814200000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.486169099807739, timestamp=1659647706.3674533) [(&#39;tile_f&#39;, [-1, 8, 4, 4]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#39;tile_x&#39;, [-1, 1, 1, 7]), (&#39;tile_rc&#39;, [-1, 4, 1]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 0)],None,2140058
+No: 17  GFLOPS: 0.00/260.07     result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 142, in build
     res = future.result()
   File &quot;/usr/lib/python3.7/concurrent/futures/_base.py&quot;, line 435, in result
@@ -1950,8 +1950,8 @@ No: 17  GFLOPS: 0.00/261.10     result: Traceback (most recent call last):
 TimeoutError
 
         [(&#39;tile_f&#39;, [-1, 2, 2, 1]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 4, 16]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 1)],None,10195251
-No: 18  GFLOPS: 28.12/261.10    result: MeasureResult(costs=(0.008231936142857143,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3359155654907227, timestamp=1659640936.1278422)       [(&#39;tile_f&#39;, [-1, 4, 8, 4]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 1, 4]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 1)],None,6068603
-No: 19  GFLOPS: 0.00/261.10     result: Traceback (most recent call last):
+No: 18  GFLOPS: 28.05/260.07    result: MeasureResult(costs=(0.008254217285714285,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.293917179107666, timestamp=1659647717.3834984)        [(&#39;tile_f&#39;, [-1, 4, 8, 4]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 1, 4]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 1)],None,6068603
+No: 19  GFLOPS: 0.00/260.07     result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 588, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 540, in _build_func_common
@@ -2074,7 +2074,7 @@ Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 871, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
 tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 16, 4, 8]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 4, 128]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 1)],None,6956993
-No: 20  GFLOPS: 0.00/261.10     result: Traceback (most recent call last):
+No: 20  GFLOPS: 0.00/260.07     result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 588, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 540, in _build_func_common
@@ -2237,7 +2237,7 @@ and measure running time.</p>
 Best config:
 [(&#39;tile_f&#39;, [-1, 8, 2, 1]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 2, 1]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 0)],None,4264713
 Finish loading 20 records
-Time cost of this operator: 0.001262
+Time cost of this operator: 0.001240
 </pre></div>
 </div>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autotvm-tune-conv2d-cuda-py">
diff --git a/docs/how_to/work_with_microtvm/micro_autotune.html b/docs/how_to/work_with_microtvm/micro_autotune.html
index 52dfa6e84..113465e0b 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -584,10 +584,10 @@ the tuned operator.</p>
 ########## Build without Autotuning ##########
 Node Name                                     Ops                                           Time(us)  Time(%)  Shape              Inputs  Outputs  Measurements(us)
 ---------                                     ---                                           --------  -------  -----              ------  -------  ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  311.1     98.732   (1, 2, 10, 10, 3)  2       1        [311.1]
-tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       3.015     0.957    (1, 6, 10, 10)     1       1        [3.015]
-tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.979     0.311    (1, 1, 10, 10, 3)  1       1        [0.979]
-Total_time                                    -                                             315.094   -        -                  -       -        -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  318.1     98.76    (1, 2, 10, 10, 3)  2       1        [318.1]
+tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       3.03      0.941    (1, 6, 10, 10)     1       1        [3.03]
+tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.965     0.3      (1, 1, 10, 10, 3)  1       1        [0.965]
+Total_time                                    -                                             322.095   -        -                  -       -        -
 </pre></div>
 </div>
 </div>
@@ -640,10 +640,10 @@ Total_time                                    -
 ########## Build with Autotuning ##########
 Node Name                                     Ops                                           Time(us)  Time(%)  Shape              Inputs  Outputs  Measurements(us)
 ---------                                     ---                                           --------  -------  -----              ------  -------  ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  93.438    97.252   (1, 6, 10, 10, 1)  2       1        [93.438]
-tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       1.777     1.85     (1, 6, 10, 10)     1       1        [1.777]
-tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.863     0.899    (1, 3, 10, 10, 1)  1       1        [0.863]
-Total_time                                    -                                             96.078    -        -                  -       -        -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  195.6     98.675   (1, 6, 10, 10, 1)  2       1        [195.6]
+tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       1.784     0.9      (1, 6, 10, 10)     1       1        [1.784]
+tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.842     0.425    (1, 3, 10, 10, 1)  1       1        [0.842]
+Total_time                                    -                                             198.226   -        -                  -       -        -
 </pre></div>
 </div>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index 879382de0..c60274d6f 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -516,7 +516,7 @@ take about <strong>2 minutes</strong> to download the Stanford Cars, while COCO
 <a href="https://docs.python.org/3/library/shutil.html#shutil.move" title="shutil.move" class="sphx-glr-backref-module-shutil sphx-glr-backref-type-py-function"><span class="n">shutil</span><span class="o">.</span><span class="n">move</span></a><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;</span><span class="si">{</span><a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-typ [...]
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>&#39;/tmp/tmpcj34n6x6/images/random&#39;
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>&#39;/tmp/tmp3bpw5n69/images/random&#39;
 </pre></div>
 </div>
 </div>
@@ -576,8 +576,8 @@ objects to other stuff? We can display some examples from our datasets using <co
     <span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">&quot;off&quot;</span><span class="p">)</span>
 </pre></div>
 </div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpcj34n6x6/images/target contains 8144 images
-/tmp/tmpcj34n6x6/images/random contains 5000 images
+<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmp3bpw5n69/images/target contains 8144 images
+/tmp/tmp3bpw5n69/images/random contains 5000 images
 </pre></div>
 </div>
 </div>
@@ -689,13 +689,13 @@ the time on our validation set).</p>
 </pre></div>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 55s - loss: 0.2667 - accuracy: 0.9124 - val_loss: 0.1268 - val_accuracy: 0.9558
+328/328 - 55s - loss: 0.2374 - accuracy: 0.9198 - val_loss: 0.1366 - val_accuracy: 0.9596
 Epoch 2/3
-328/328 - 52s - loss: 0.1080 - accuracy: 0.9607 - val_loss: 0.1114 - val_accuracy: 0.9637
+328/328 - 52s - loss: 0.1010 - accuracy: 0.9627 - val_loss: 0.1120 - val_accuracy: 0.9641
 Epoch 3/3
-328/328 - 52s - loss: 0.0709 - accuracy: 0.9731 - val_loss: 0.1705 - val_accuracy: 0.9464
+328/328 - 52s - loss: 0.0697 - accuracy: 0.9747 - val_loss: 0.2233 - val_accuracy: 0.9415
 
-&lt;keras.callbacks.History object at 0x7fe15997f390&gt;
+&lt;keras.callbacks.History object at 0x7f5ce46c9510&gt;
 </pre></div>
 </div>
 </div>
@@ -957,7 +957,7 @@ as intended.</p>
 <p>From here, we could modify the model to read live images from the camera - we have another
 Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
 <a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes  50.438 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes  51.736 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 febb607c1..bfb941362 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -327,7 +327,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:43.464</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>05:45.541</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 83%" />
@@ -336,19 +336,19 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>04:50.438</p></td>
+<td><p>04:51.736</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:41.751</p></td>
+<td><p>00:41.903</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="micro_aot.html#sphx-glr-how-to-work-with-microtvm-micro-aot-py"><span class="std std-ref">microTVM Host-Driven AoT</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:08.001</p></td>
+<td><p>00:08.607</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:03.271</p></td>
+<td><p>00:03.293</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_relay/sg_execution_times.html b/docs/how_to/work_with_relay/sg_execution_times.html
index 2268aab68..5c6821d2d 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -327,7 +327,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:41.589</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:41.109</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 84%" />
@@ -336,15 +336,15 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="using_pipeline_executor.html#sphx-glr-how-to-work-with-relay-using-pipeline-executor-py"><span class="std std-ref">Using Pipeline Executor in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_pipeline_executor.py</span></code>)</p></td>
-<td><p>00:30.153</p></td>
+<td><p>00:29.861</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></td>
-<td><p>00:09.834</p></td>
+<td><p>00:09.748</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>00:01.595</p></td>
+<td><p>00:01.493</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 84473c7dc..eacd1fccc 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -522,7 +522,7 @@ The following example customizes CUDA lowering rule for <code class="code docuti
 <a href="../../reference/api/python/ir.html#tvm.ir.register_intrin_lowering" title="tvm.ir.register_intrin_lowering" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-function"><span class="n">register_intrin_lowering</span></a><span class="p">(</span><span class="s2">&quot;tir.exp&quot;</span><span class="p">,</span> <span class="n">target</span><span class="o">=</span><span class="s2">&quot;cuda&quot;</span><span class="p">,</span> <span class="n">f</span><span class="o">= [...]
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>&lt;function my_cuda_math_rule at 0x7fe1592b24d0&gt;
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>&lt;function my_cuda_math_rule at 0x7f5caef6a8c0&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 f79d4c754..0e4513025 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -327,7 +327,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:04.111</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:04.011</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 83%" />
@@ -336,11 +336,11 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:01.854</p></td>
+<td><p>00:01.857</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>00:01.014</p></td>
+<td><p>00:00.930</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>
@@ -348,15 +348,15 @@
 <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>00:00.512</p></td>
+<td><p>00:00.505</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="extern_op.html#sphx-glr-how-to-work-with-schedules-extern-op-py"><span class="std std-ref">External Tensor Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">extern_op.py</span></code>)</p></td>
-<td><p>00:00.130</p></td>
+<td><p>00:00.120</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
-<td><p>00:00.041</p></td>
+<td><p>00:00.040</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 062dcb680..48e6ed86f 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -577,7 +577,7 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
              C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
   buffer_map = {A_1: A, B_1: B, C_1: C}
   preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
-  attr [IterVar(i: int32, (nullptr), &quot;DataPar&quot;, &quot;&quot;)] &quot;pragma_import_llvm&quot; = &quot;; ModuleID = &#39;/tmp/tmppyh3n01m/input0.cc&#39;\nsource_filename = \&quot;/tmp/tmppyh3n01m/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/tmplfqlw9m8/input0.cc&#39;\nsource_filename = \&quot;/tmp/tmplfqlw9m8/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/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 2fe1e1916..cb722a151 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1602,7 +1602,7 @@ history states as starting point to perform Evolutionary Search).</p></li>
 
 <dl class="py class">
 <dt class="sig sig-object py" id="tvm.auto_scheduler.SketchPolicy">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
 <dd><p>The search policy that searches in a hierarchical search space defined by sketches.
 The policy randomly samples programs from the space defined by sketches and use evolutionary
 search to fine-tune them.</p>
@@ -1886,7 +1886,7 @@ Candidates:
 
 <dl class="py function">
 <dt class="sig sig-object py" id="tvm.auto_scheduler.auto_schedule">
-<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
 <dd><p>THIS API IS DEPRECATED.</p>
 <p>Run auto scheduling search for a task.</p>
 <dl class="field-list simple">
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index 714bf96d8..ef878da5a 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/cfa55251b/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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 9a3d2daf2..0da0b509e 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/cfa55251b/web/src/memory.ts#L223">memory.ts:223</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/memory.ts#L208">memory.ts:208</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/memory.ts#L312">memory.ts:312</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/memory.ts#L284">memory.ts:284</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/memory.ts#L388">memory.ts:388</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/memory.ts#L376">memory.ts:376</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/memory.ts#L267">memory.ts:267</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/memory.ts#L243">memory.ts:243</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/memory.ts#L321">memory.ts:321</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/memory.ts#L252">memory.ts:252</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/memory.ts#L359">memory.ts:359</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/memory.ts#L342">memory.ts:342</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/memory.ts#L350">memory.ts:350</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/memory.ts#L326">memory.ts:326</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/memory.ts#L363">memory.ts:363</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/memory.ts#L346">memory.ts:346</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/memory.ts#L334">memory.ts:334</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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 c89703048..444703b9b 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/cfa55251b/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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 d4d4db049..d4054d926 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/cfa55251b/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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 4dac25be7..7f8bfb0b2 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/cfa55251b/web/src/environment.ts#L86">environment.ts:86</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/environment.ts#L70">environment.ts:70</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/environment.ts#L69">environment.ts:69</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/environment.ts#L78">environment.ts:78</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/environment.ts#L84">environment.ts:84</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/environment.ts#L105">environment.ts:105</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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 d2c60ebd6..979619200 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/cfa55251b/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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 ddd7d5d39..4776dc640 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/cfa55251b/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/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/cfa55251b/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L644">runtime.ts:644</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -310,7 +310,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L621">runtime.ts:621</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -332,7 +332,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L609">runtime.ts:609</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/instance.html b/docs/reference/api/typedoc/classes/instance.html
index fa0be1dfc..beac9a9d5 100644
--- a/docs/reference/api/typedoc/classes/instance.html
+++ b/docs/reference/api/typedoc/classes/instance.html
@@ -139,7 +139,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L692">runtime.ts:692</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -202,7 +202,7 @@
 					<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol">&lt;</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">&gt;</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L684">runtime.ts:684</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -212,7 +212,7 @@
 					<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L683">runtime.ts:683</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -229,7 +229,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L932">runtime.ts:932</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -260,7 +260,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L994">runtime.ts:994</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -303,7 +303,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L924">runtime.ts:924</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -341,7 +341,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L732">runtime.ts:732</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -358,7 +358,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L952">runtime.ts:952</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -402,7 +402,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L816">runtime.ts:816</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -434,7 +434,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -465,7 +465,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L846">runtime.ts:846</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -497,7 +497,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L750">runtime.ts:750</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -520,7 +520,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -568,7 +568,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L789">runtime.ts:789</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -608,7 +608,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L914">runtime.ts:914</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -646,7 +646,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L1140">runtime.ts:1140</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L1140">runtime.ts:1140</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -698,7 +698,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L740">runtime.ts:740</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -722,7 +722,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L868">runtime.ts:868</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -754,7 +754,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L857">runtime.ts:857</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -786,7 +786,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L940">runtime.ts:940</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/memory.html b/docs/reference/api/typedoc/classes/memory.html
index 0ada6ec1f..a482e0ae3 100644
--- a/docs/reference/api/typedoc/classes/memory.html
+++ b/docs/reference/api/typedoc/classes/memory.html
@@ -130,7 +130,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/memory.ts#L40">memory.ts:40</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/memory.ts#L40">memory.ts:40</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -152,7 +152,7 @@
 					<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Memory</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/memory.ts#L32">memory.ts:32</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/memory.ts#L32">memory.ts:32</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -162,7 +162,7 @@
 					<div class="tsd-signature tsd-kind-icon">wasm32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">boolean</span><span class="tsd-signature-symbol"> = true</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/memory.ts#L33">memory.ts:33</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/memory.ts#L33">memory.ts:33</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -179,7 +179,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/memory.ts#L154">memory.ts:154</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/memory.ts#L154">memory.ts:154</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -210,7 +210,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/memory.ts#L90">memory.ts:90</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/memory.ts#L90">memory.ts:90</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -233,7 +233,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/memory.ts#L97">memory.ts:97</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/memory.ts#L97">memory.ts:97</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -256,7 +256,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/memory.ts#L74">memory.ts:74</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/memory.ts#L74">memory.ts:74</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -279,7 +279,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/memory.ts#L81">memory.ts:81</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/memory.ts#L81">memory.ts:81</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -302,7 +302,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/memory.ts#L104">memory.ts:104</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/memory.ts#L104">memory.ts:104</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -325,7 +325,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/memory.ts#L132">memory.ts:132</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/memory.ts#L132">memory.ts:132</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -362,7 +362,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/memory.ts#L145">memory.ts:145</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/memory.ts#L145">memory.ts:145</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -393,7 +393,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/memory.ts#L60">memory.ts:60</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/memory.ts#L60">memory.ts:60</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -416,7 +416,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/memory.ts#L67">memory.ts:67</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/memory.ts#L67">memory.ts:67</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -439,7 +439,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/memory.ts#L53">memory.ts:53</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/memory.ts#L53">memory.ts:53</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -462,7 +462,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/memory.ts#L114">memory.ts:114</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/memory.ts#L114">memory.ts:114</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -485,7 +485,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/memory.ts#L124">memory.ts:124</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/memory.ts#L124">memory.ts:124</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -502,7 +502,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/memory.ts#L175">memory.ts:175</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/memory.ts#L175">memory.ts:175</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/module.html b/docs/reference/api/typedoc/classes/module.html
index 85dedec94..2d2192163 100644
--- a/docs/reference/api/typedoc/classes/module.html
+++ b/docs/reference/api/typedoc/classes/module.html
@@ -124,7 +124,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L504">runtime.ts:504</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -170,7 +170,7 @@
 					<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L502">runtime.ts:502</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -187,7 +187,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L516">runtime.ts:516</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -204,7 +204,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L530">runtime.ts:530</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -236,7 +236,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L561">runtime.ts:561</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/ndarray.html b/docs/reference/api/typedoc/classes/ndarray.html
index 41354b3da..e8c2b2997 100644
--- a/docs/reference/api/typedoc/classes/ndarray.html
+++ b/docs/reference/api/typedoc/classes/ndarray.html
@@ -130,7 +130,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L304">runtime.ts:304</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -158,7 +158,7 @@
 					<div class="tsd-signature tsd-kind-icon">device<span class="tsd-signature-symbol">:</span> <a href="dldevice.html" class="tsd-signature-type">DLDevice</a></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L297">runtime.ts:297</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -173,7 +173,7 @@
 					<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L293">runtime.ts:293</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -188,7 +188,7 @@
 					<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L289">runtime.ts:289</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -203,7 +203,7 @@
 					<div class="tsd-signature tsd-kind-icon">ndim<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L291">runtime.ts:291</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -218,7 +218,7 @@
 					<div class="tsd-signature tsd-kind-icon">shape<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol">&lt;</span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">&gt;</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L295">runtime.ts:295</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -240,7 +240,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L370">runtime.ts:370</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -273,7 +273,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L414">runtime.ts:414</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -305,7 +305,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L355">runtime.ts:355</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -322,7 +322,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L474">runtime.ts:474</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -346,7 +346,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L443">runtime.ts:443</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/packedfunccell.html b/docs/reference/api/typedoc/classes/packedfunccell.html
index 70ba4a5d9..b92feada1 100644
--- a/docs/reference/api/typedoc/classes/packedfunccell.html
+++ b/docs/reference/api/typedoc/classes/packedfunccell.html
@@ -122,7 +122,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L158">runtime.ts:158</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -147,7 +147,7 @@
 					<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L157">runtime.ts:157</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -164,7 +164,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L165">runtime.ts:165</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
diff --git a/docs/reference/api/typedoc/classes/rpcserver.html b/docs/reference/api/typedoc/classes/rpcserver.html
index 9e3806e21..93a971749 100644
--- a/docs/reference/api/typedoc/classes/rpcserver.html
+++ b/docs/reference/api/typedoc/classes/rpcserver.html
@@ -115,7 +115,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -176,7 +176,7 @@
 					<div class="tsd-signature tsd-kind-icon">get<wbr>Imports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&gt; </span><span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol">&lt;</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">unknown</span><span class="tsd-signat [...]
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-type-declaration">
@@ -201,7 +201,7 @@
 					<div class="tsd-signature tsd-kind-icon">key<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -211,7 +211,7 @@
 					<div class="tsd-signature tsd-kind-icon">logger<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>msg<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&gt; </span><span class="tsd-signature-type">void</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-type-declaration">
@@ -242,7 +242,7 @@
 					<div class="tsd-signature tsd-kind-icon">socket<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">WebSocket</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -252,7 +252,7 @@
 					<div class="tsd-signature tsd-kind-icon">state<span class="tsd-signature-symbol">:</span> <a href="../enums/rpcserverstate.html" class="tsd-signature-type">RPCServerState</a><span class="tsd-signature-symbol"> = RPCServerState.InitHeader</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -262,7 +262,7 @@
 					<div class="tsd-signature tsd-kind-icon">url<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
 						</ul>
 					</aside>
 				</section>
diff --git a/docs/reference/api/typedoc/classes/scalar.html b/docs/reference/api/typedoc/classes/scalar.html
index 6c316190a..368bee9fd 100644
--- a/docs/reference/api/typedoc/classes/scalar.html
+++ b/docs/reference/api/typedoc/classes/scalar.html
@@ -112,7 +112,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L145">runtime.ts:145</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -137,7 +137,7 @@
 					<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L145">runtime.ts:145</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -152,7 +152,7 @@
 					<div class="tsd-signature tsd-kind-icon">value<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L143">runtime.ts:143</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/webgpucontext.html b/docs/reference/api/typedoc/classes/webgpucontext.html
index dfd58780b..5aaedd5ec 100644
--- a/docs/reference/api/typedoc/classes/webgpucontext.html
+++ b/docs/reference/api/typedoc/classes/webgpucontext.html
@@ -120,7 +120,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
 								</ul>
 							</aside>
 							<h4 class="tsd-parameters-title">Parameters</h4>
@@ -145,7 +145,7 @@
 					<div class="tsd-signature tsd-kind-icon">device<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">GPUDevice</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -155,7 +155,7 @@
 					<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -172,7 +172,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -209,7 +209,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/enums/argtypecode.html b/docs/reference/api/typedoc/enums/argtypecode.html
index 22ad49ea4..6867992e3 100644
--- a/docs/reference/api/typedoc/enums/argtypecode.html
+++ b/docs/reference/api/typedoc/enums/argtypecode.html
@@ -106,7 +106,7 @@
 					<div class="tsd-signature tsd-kind-icon">DLDevice<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 6</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -116,7 +116,7 @@
 					<div class="tsd-signature tsd-kind-icon">Float<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -126,7 +126,7 @@
 					<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -136,7 +136,7 @@
 					<div class="tsd-signature tsd-kind-icon">Null<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -146,7 +146,7 @@
 					<div class="tsd-signature tsd-kind-icon">TVMBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 12</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -156,7 +156,7 @@
 					<div class="tsd-signature tsd-kind-icon">TVMDLTensor<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 7</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -166,7 +166,7 @@
 					<div class="tsd-signature tsd-kind-icon">TVMData<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 5</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -176,7 +176,7 @@
 					<div class="tsd-signature tsd-kind-icon">TVMModule<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 9</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -186,7 +186,7 @@
 					<div class="tsd-signature tsd-kind-icon">TVMNDArray<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 13</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -196,7 +196,7 @@
 					<div class="tsd-signature tsd-kind-icon">TVMObject<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -206,7 +206,7 @@
 					<div class="tsd-signature tsd-kind-icon">TVMObjectRValue<wbr>Ref<wbr>Arg<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 14</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -216,7 +216,7 @@
 					<div class="tsd-signature tsd-kind-icon">TVMOpaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -226,7 +226,7 @@
 					<div class="tsd-signature tsd-kind-icon">TVMPacked<wbr>Func<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 10</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -236,7 +236,7 @@
 					<div class="tsd-signature tsd-kind-icon">TVMStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 11</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -246,7 +246,7 @@
 					<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
 						</ul>
 					</aside>
 				</section>
diff --git a/docs/reference/api/typedoc/enums/aynccallbackcode.html b/docs/reference/api/typedoc/enums/aynccallbackcode.html
index 8d56e1a42..63ab904d9 100644
--- a/docs/reference/api/typedoc/enums/aynccallbackcode.html
+++ b/docs/reference/api/typedoc/enums/aynccallbackcode.html
@@ -93,7 +93,7 @@
 					<div class="tsd-signature tsd-kind-icon">k<wbr>Exception<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 5</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L676">runtime.ts:676</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -103,7 +103,7 @@
 					<div class="tsd-signature tsd-kind-icon">k<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L675">runtime.ts:675</a></li>
 						</ul>
 					</aside>
 				</section>
diff --git a/docs/reference/api/typedoc/enums/dldatatypecode.html b/docs/reference/api/typedoc/enums/dldatatypecode.html
index 5dd3dd300..de98ecad8 100644
--- a/docs/reference/api/typedoc/enums/dldatatypecode.html
+++ b/docs/reference/api/typedoc/enums/dldatatypecode.html
@@ -95,7 +95,7 @@
 					<div class="tsd-signature tsd-kind-icon">Float<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L242">runtime.ts:242</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -105,7 +105,7 @@
 					<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L240">runtime.ts:240</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -115,7 +115,7 @@
 					<div class="tsd-signature tsd-kind-icon">Opaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L243">runtime.ts:243</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -125,7 +125,7 @@
 					<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L241">runtime.ts:241</a></li>
 						</ul>
 					</aside>
 				</section>
diff --git a/docs/reference/api/typedoc/enums/rpcserverstate.html b/docs/reference/api/typedoc/enums/rpcserverstate.html
index 25156e334..09136c62c 100644
--- a/docs/reference/api/typedoc/enums/rpcserverstate.html
+++ b/docs/reference/api/typedoc/enums/rpcserverstate.html
@@ -90,7 +90,7 @@
 					<div class="tsd-signature tsd-kind-icon">Init<wbr>Header<span class="tsd-signature-symbol">:</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -100,7 +100,7 @@
 					<div class="tsd-signature tsd-kind-icon">Init<wbr>Header<wbr>Key<span class="tsd-signature-symbol">:</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -110,7 +110,7 @@
 					<div class="tsd-signature tsd-kind-icon">Init<wbr>Server<span class="tsd-signature-symbol">:</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -120,7 +120,7 @@
 					<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Body<span class="tsd-signature-symbol">:</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -130,7 +130,7 @@
 					<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Header<span class="tsd-signature-symbol">:</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -140,7 +140,7 @@
 					<div class="tsd-signature tsd-kind-icon">Wait<wbr>For<wbr>Callback<span class="tsd-signature-symbol">:</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
 						</ul>
 					</aside>
 				</section>
diff --git a/docs/reference/api/typedoc/enums/sizeof.html b/docs/reference/api/typedoc/enums/sizeof.html
index 23ac329df..3b16c9fbb 100644
--- a/docs/reference/api/typedoc/enums/sizeof.html
+++ b/docs/reference/api/typedoc/enums/sizeof.html
@@ -100,7 +100,7 @@
 					<div class="tsd-signature tsd-kind-icon">DLData<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = I32</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -110,7 +110,7 @@
 					<div class="tsd-signature tsd-kind-icon">DLDevice<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = I32 + I32</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -120,7 +120,7 @@
 					<div class="tsd-signature tsd-kind-icon">F32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -130,7 +130,7 @@
 					<div class="tsd-signature tsd-kind-icon">F64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -140,7 +140,7 @@
 					<div class="tsd-signature tsd-kind-icon">I32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -150,7 +150,7 @@
 					<div class="tsd-signature tsd-kind-icon">I64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -160,7 +160,7 @@
 					<div class="tsd-signature tsd-kind-icon">TVMValue<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -170,7 +170,7 @@
 					<div class="tsd-signature tsd-kind-icon">U16<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -180,7 +180,7 @@
 					<div class="tsd-signature tsd-kind-icon">U8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
 						</ul>
 					</aside>
 				</section>
diff --git a/docs/reference/api/typedoc/index.html b/docs/reference/api/typedoc/index.html
index aefd1af1e..4d22b4ec1 100644
--- a/docs/reference/api/typedoc/index.html
+++ b/docs/reference/api/typedoc/index.html
@@ -174,7 +174,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Alloc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>shape<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, ndim<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeCode<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeBits<span class="tsd [...]
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>Bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">num [...]
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -282,7 +282,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>To<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>from<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, to<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-sig [...]
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -326,7 +326,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>ToBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</sp [...]
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -370,7 +370,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&gt; </span><span class="tsd-signature-type">number</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -406,7 +406,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMBackend<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number< [...]
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -458,7 +458,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMCFunc<wbr>Set<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ret<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signa [...]
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -506,7 +506,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMCb<wbr>Arg<wbr>ToReturn<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, code<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&gt; </span><span c [...]
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -545,7 +545,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Call<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-t [...]
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -601,7 +601,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&gt; </span><span class="tsd-signature-type">number</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -637,7 +637,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Get<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&gt; </span><span cla [...]
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -676,7 +676,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>List<wbr>Global<wbr>Names<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>outSize<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, outArray<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -715,7 +715,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Register<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, f<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, override<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</spa [...]
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -758,7 +758,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMGet<wbr>Last<wbr>Error<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&gt; </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -788,7 +788,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&gt; </span><span class="tsd-signature-type">number</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -824,7 +824,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Get<wbr>Function<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, funcName<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, queryImports<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">numbe [...]
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -872,7 +872,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Import<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, dep<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&gt; </span><span class="tsd-si [...]
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -912,7 +912,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMSynchronize<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>deviceType<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, deviceId<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signatur [...]
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -954,7 +954,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Alloc<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>size<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&gt; </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -990,7 +990,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Free<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ptr<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&gt; </span><span class="tsd-signature-type">void</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -1026,7 +1026,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Func<wbr>Create<wbr>FromCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resource<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -1066,7 +1066,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>args<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, [...]
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -1118,7 +1118,7 @@
 					<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<wbr>Finalizer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resourceHandle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&gt; </span><span class="tsd-signature-type">void</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -1154,7 +1154,7 @@
 					<div class="tsd-signature tsd-kind-icon">GPUPointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -1169,7 +1169,7 @@
 					<div class="tsd-signature tsd-kind-icon">Packed<wbr>Func<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">...</span>args<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&gt; </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol"> &amp; </span><a href="interfaces/disp [...]
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L36">runtime.ts:36</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -1184,7 +1184,7 @@
 					<div class="tsd-signature tsd-kind-icon">Pointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -1199,7 +1199,7 @@
 					<div class="tsd-signature tsd-kind-icon">Ptr<wbr>Offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -1217,7 +1217,7 @@
 					<div class="tsd-signature tsd-kind-icon">RPC_<wbr>MAGIC<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">1045105</span><span class="tsd-signature-symbol"> = 1045105</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -1239,7 +1239,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/support.ts#L25">support.ts:25</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/support.ts#L25">support.ts:25</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -1271,7 +1271,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/support.ts#L39">support.ts:39</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/support.ts#L39">support.ts:39</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -1300,7 +1300,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/support.ts#L52">support.ts:52</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/support.ts#L52">support.ts:52</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -1337,7 +1337,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/compact.ts#L38">compact.ts:38</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/compact.ts#L38">compact.ts:38</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -1368,7 +1368,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -1390,7 +1390,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/environment.ts#L32">environment.ts:32</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/environment.ts#L32">environment.ts:32</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -1421,7 +1421,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/compact.ts#L24">compact.ts:24</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/compact.ts#L24">compact.ts:24</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -1443,7 +1443,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L1362">runtime.ts:1362</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L1362">runtime.ts:1362</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -1508,7 +1508,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/support.ts#L62">support.ts:62</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/support.ts#L62">support.ts:62</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -1530,7 +1530,7 @@
 					<div class="tsd-signature tsd-kind-icon">DLData<wbr>Type<wbr>Code<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L246">runtime.ts:246</a></li>
 						</ul>
 					</aside>
 					<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1539,7 +1539,7 @@
 						<div class="tsd-signature tsd-kind-icon">0<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = &quot;int&quot;</span></div>
 						<aside class="tsd-sources">
 							<ul>
-								<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L247">runtime.ts:247</a></li>
 							</ul>
 						</aside>
 					</section>
@@ -1549,7 +1549,7 @@
 						<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = &quot;uint&quot;</span></div>
 						<aside class="tsd-sources">
 							<ul>
-								<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L248">runtime.ts:248</a></li>
 							</ul>
 						</aside>
 					</section>
@@ -1559,7 +1559,7 @@
 						<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = &quot;float&quot;</span></div>
 						<aside class="tsd-sources">
 							<ul>
-								<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L249">runtime.ts:249</a></li>
 							</ul>
 						</aside>
 					</section>
@@ -1569,7 +1569,7 @@
 						<div class="tsd-signature tsd-kind-icon">3<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = &quot;handle&quot;</span></div>
 						<aside class="tsd-sources">
 							<ul>
-								<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L250">runtime.ts:250</a></li>
 							</ul>
 						</aside>
 					</section>
@@ -1580,7 +1580,7 @@
 					<div class="tsd-signature tsd-kind-icon">Device<wbr>Enum<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L175">runtime.ts:175</a></li>
 						</ul>
 					</aside>
 					<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1589,7 +1589,7 @@
 						<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = &quot;cpu&quot;</span></div>
 						<aside class="tsd-sources">
 							<ul>
-								<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L176">runtime.ts:176</a></li>
 							</ul>
 						</aside>
 					</section>
@@ -1599,7 +1599,7 @@
 						<div class="tsd-signature tsd-kind-icon">15<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = &quot;webgpu&quot;</span></div>
 						<aside class="tsd-sources">
 							<ul>
-								<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L180">runtime.ts:180</a></li>
 							</ul>
 						</aside>
 					</section>
@@ -1609,7 +1609,7 @@
 						<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = &quot;cuda&quot;</span></div>
 						<aside class="tsd-sources">
 							<ul>
-								<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L177">runtime.ts:177</a></li>
 							</ul>
 						</aside>
 					</section>
@@ -1619,7 +1619,7 @@
 						<div class="tsd-signature tsd-kind-icon">4<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = &quot;opencl&quot;</span></div>
 						<aside class="tsd-sources">
 							<ul>
-								<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L178">runtime.ts:178</a></li>
 							</ul>
 						</aside>
 					</section>
@@ -1629,7 +1629,7 @@
 						<div class="tsd-signature tsd-kind-icon">8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = &quot;metal&quot;</span></div>
 						<aside class="tsd-sources">
 							<ul>
-								<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L179">runtime.ts:179</a></li>
 							</ul>
 						</aside>
 					</section>
@@ -1640,7 +1640,7 @@
 					<div class="tsd-signature tsd-kind-icon">Device<wbr>Str<wbr>ToEnum<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L183">runtime.ts:183</a></li>
 						</ul>
 					</aside>
 					<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1649,7 +1649,7 @@
 						<div class="tsd-signature tsd-kind-icon">cl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
 						<aside class="tsd-sources">
 							<ul>
-								<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L186">runtime.ts:186</a></li>
 							</ul>
 						</aside>
 					</section>
@@ -1659,7 +1659,7 @@
 						<div class="tsd-signature tsd-kind-icon">cpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 1</span></div>
 						<aside class="tsd-sources">
 							<ul>
-								<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L184">runtime.ts:184</a></li>
 							</ul>
 						</aside>
 					</section>
@@ -1669,7 +1669,7 @@
 						<div class="tsd-signature tsd-kind-icon">cuda<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 2</span></div>
 						<aside class="tsd-sources">
 							<ul>
-								<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L185">runtime.ts:185</a></li>
 							</ul>
 						</aside>
 					</section>
@@ -1679,7 +1679,7 @@
 						<div class="tsd-signature tsd-kind-icon">metal<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 8</span></div>
 						<aside class="tsd-sources">
 							<ul>
-								<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L189">runtime.ts:189</a></li>
 							</ul>
 						</aside>
 					</section>
@@ -1689,7 +1689,7 @@
 						<div class="tsd-signature tsd-kind-icon">opencl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
 						<aside class="tsd-sources">
 							<ul>
-								<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L187">runtime.ts:187</a></li>
 							</ul>
 						</aside>
 					</section>
@@ -1699,7 +1699,7 @@
 						<div class="tsd-signature tsd-kind-icon">vulkan<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 7</span></div>
 						<aside class="tsd-sources">
 							<ul>
-								<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L188">runtime.ts:188</a></li>
 							</ul>
 						</aside>
 					</section>
@@ -1709,7 +1709,7 @@
 						<div class="tsd-signature tsd-kind-icon">webgpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 15</span></div>
 						<aside class="tsd-sources">
 							<ul>
-								<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/runtime.ts#L190">runtime.ts:190</a></li>
 							</ul>
 						</aside>
 					</section>
diff --git a/docs/reference/api/typedoc/interfaces/disposable.html b/docs/reference/api/typedoc/interfaces/disposable.html
index 975f20b69..56f82b5a5 100644
--- a/docs/reference/api/typedoc/interfaces/disposable.html
+++ b/docs/reference/api/typedoc/interfaces/disposable.html
@@ -113,7 +113,7 @@
 					<div class="tsd-signature tsd-kind-icon">dispose<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&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/cfa55251b/web/src/types.ts#L52">types.ts:52</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/types.ts#L52">types.ts:52</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/interfaces/functioninfo.html b/docs/reference/api/typedoc/interfaces/functioninfo.html
index fdf3de7ec..24855141a 100644
--- a/docs/reference/api/typedoc/interfaces/functioninfo.html
+++ b/docs/reference/api/typedoc/interfaces/functioninfo.html
@@ -95,7 +95,7 @@
 					<div class="tsd-signature tsd-kind-icon">arg_<wbr>types<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol">&lt;</span><span class="tsd-signature-type">string</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/cfa55251b/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -105,7 +105,7 @@
 					<div class="tsd-signature tsd-kind-icon">launch_<wbr>param_<wbr>tags<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol">&lt;</span><span class="tsd-signature-type">string</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/cfa55251b/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
 						</ul>
 					</aside>
 				</section>
@@ -115,7 +115,7 @@
 					<div class="tsd-signature tsd-kind-icon">name<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
 						</ul>
 					</aside>
 				</section>
diff --git a/docs/reference/api/typedoc/interfaces/libraryprovider.html b/docs/reference/api/typedoc/interfaces/libraryprovider.html
index e5b18b040..7e557927c 100644
--- a/docs/reference/api/typedoc/interfaces/libraryprovider.html
+++ b/docs/reference/api/typedoc/interfaces/libraryprovider.html
@@ -112,7 +112,7 @@
 					<div class="tsd-signature tsd-kind-icon">imports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol">&lt;</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol">&gt;</span></div>
 					<aside class="tsd-sources">
 						<ul>
-							<li>Defined in <a href="https://github.com/apache/tvm/blob/cfa55251b/web/src/types.ts#L34">types.ts:34</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/types.ts#L34">types.ts:34</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
@@ -127,7 +127,7 @@
 					<div class="tsd-signature tsd-kind-icon">start<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>inst<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">Instance</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&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/cfa55251b/web/src/types.ts#L39">types.ts:39</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/2866f315f/web/src/types.ts#L39">types.ts:39</a></li>
 						</ul>
 					</aside>
 					<div class="tsd-comment tsd-typography">
diff --git a/docs/searchindex.js b/docs/searchindex.js
index fed1ec884..a6393cdd2 100644
--- a/docs/searchindex.js
+++ b/docs/searchindex.js
@@ -1 +1 @@
-Search.setIndex({docnames:["arch/benchmark","arch/convert_layout","arch/debugger","arch/device_target_interactions","arch/frontend/tensorflow","arch/hybrid_script","arch/index","arch/inferbound","arch/introduction_to_module_serialization","arch/microtvm_design","arch/microtvm_project_api","arch/model_library_format","arch/pass_infra","arch/relay_intro","arch/relay_op_strategy","arch/runtime","arch/runtimes/vulkan","arch/security","arch/virtual_machine","contribute/ci","contribute/code_gu [...]
\ No newline at end of file
+Search.setIndex({docnames:["arch/benchmark","arch/convert_layout","arch/debugger","arch/device_target_interactions","arch/frontend/tensorflow","arch/hybrid_script","arch/index","arch/inferbound","arch/introduction_to_module_serialization","arch/microtvm_design","arch/microtvm_project_api","arch/model_library_format","arch/pass_infra","arch/relay_intro","arch/relay_op_strategy","arch/runtime","arch/runtimes/vulkan","arch/security","arch/virtual_machine","contribute/ci","contribute/code_gu [...]
\ No newline at end of file
diff --git a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
index 831710e0a..513529c7e 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -327,7 +327,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-topic-vta-tutorials-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:21.199</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:21.313</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 82%" />
@@ -336,7 +336,7 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-relay-vta-py"><span class="std std-ref">Auto-tuning a convolutional network on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_vta.py</span></code>)</p></td>
-<td><p>00:21.193</p></td>
+<td><p>00:21.306</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="tune_alu_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-alu-vta-py"><span class="std std-ref">Auto-tuning a ALU fused op on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_alu_vta.py</span></code>)</p></td>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_classification.html b/docs/topic/vta/tutorials/frontend/deploy_classification.html
index b00e52d8e..6d7bc357c 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -571,7 +571,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
   DeprecationWarning,
 /workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the  new recommended usage.
   relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
-resnet18_v1 inference graph built in 22.82s!
+resnet18_v1 inference graph built in 22.80s!
 </pre></div>
 </div>
 </div>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_detection.html b/docs/topic/vta/tutorials/frontend/deploy_detection.html
index 03d8e26bf..f43f29bc4 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -589,7 +589,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
   &quot;target_host parameter is going to be deprecated. &quot;
 /workspace/python/tvm/relay/build_module.py:411: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
   DeprecationWarning,
-yolov3-tiny inference graph built in 15.99s!
+yolov3-tiny inference graph built in 16.01s!
 </pre></div>
 </div>
 </div>
diff --git a/docs/topic/vta/tutorials/frontend/sg_execution_times.html b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
index f4190e4cb..9645aebee 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -327,7 +327,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-topic-vta-tutorials-frontend-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>01:31.796</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:31.318</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 84%" />
@@ -336,11 +336,11 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="deploy_detection.html#sphx-glr-topic-vta-tutorials-frontend-deploy-detection-py"><span class="std std-ref">Deploy Pretrained Vision Detection Model from Darknet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_detection.py</span></code>)</p></td>
-<td><p>00:48.703</p></td>
+<td><p>00:48.443</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="deploy_classification.html#sphx-glr-topic-vta-tutorials-frontend-deploy-classification-py"><span class="std std-ref">Deploy Pretrained Vision Model from MxNet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_classification.py</span></code>)</p></td>
-<td><p>00:43.093</p></td>
+<td><p>00:42.875</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 </tbody>
diff --git a/docs/topic/vta/tutorials/optimize/sg_execution_times.html b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
index fa2016429..8f390a7da 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -327,7 +327,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-topic-vta-tutorials-optimize-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:03.244</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.223</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 84%" />
@@ -336,11 +336,11 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="convolution_opt.html#sphx-glr-topic-vta-tutorials-optimize-convolution-opt-py"><span class="std std-ref">2D Convolution Optimization</span></a> (<code class="docutils literal notranslate"><span class="pre">convolution_opt.py</span></code>)</p></td>
-<td><p>00:02.855</p></td>
+<td><p>00:02.835</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="matrix_multiply_opt.html#sphx-glr-topic-vta-tutorials-optimize-matrix-multiply-opt-py"><span class="std std-ref">Matrix Multiply Blocking</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply_opt.py</span></code>)</p></td>
-<td><p>00:00.389</p></td>
+<td><p>00:00.388</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 </tbody>
diff --git a/docs/topic/vta/tutorials/sg_execution_times.html b/docs/topic/vta/tutorials/sg_execution_times.html
index d2c54a7f8..6ee240728 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -327,7 +327,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-topic-vta-tutorials-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:00.718</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.715</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 81%" />
@@ -336,11 +336,11 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="matrix_multiply.html#sphx-glr-topic-vta-tutorials-matrix-multiply-py"><span class="std std-ref">Simple Matrix Multiply</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply.py</span></code>)</p></td>
-<td><p>00:00.384</p></td>
+<td><p>00:00.391</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="vta_get_started.html#sphx-glr-topic-vta-tutorials-vta-get-started-py"><span class="std std-ref">Get Started with VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">vta_get_started.py</span></code>)</p></td>
-<td><p>00:00.334</p></td>
+<td><p>00:00.325</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 </tbody>
diff --git a/docs/tutorial/auto_scheduler_matmul_x86.html b/docs/tutorial/auto_scheduler_matmul_x86.html
index 79cc973c4..3e86cd2f3 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -566,7 +566,7 @@ 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: 94.133 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 92.231 ms
 </pre></div>
 </div>
 </div>
diff --git a/docs/tutorial/autotvm_matmul_x86.html b/docs/tutorial/autotvm_matmul_x86.html
index 59fab04a1..8ff6102c1 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -668,16 +668,16 @@ reduce variance, we take 5 measurements and average them.</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>waiting for device...
 device available
 Get devices for measurement successfully!
-No: 1   GFLOPS: 10.12/10.12     result: MeasureResult(costs=(0.026527394399999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5617697238922119, timestamp=1659639714.1637657)       [(&#39;tile_y&#39;, [-1, 1]), (&#39;tile_x&#39;, [-1, 256])],None,80
-No: 2   GFLOPS: 2.52/10.12      result: MeasureResult(costs=(0.10634097180000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8425731658935547, timestamp=1659639716.0257695)        [(&#39;tile_y&#39;, [-1, 4]), (&#39;tile_x&#39;, [-1, 8])],None,32
-No: 3   GFLOPS: 11.85/11.85     result: MeasureResult(costs=(0.0226621396,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5546488761901855, timestamp=1659639717.071295)        [(&#39;tile_y&#39;, [-1, 64]), (&#39;tile_x&#39;, [-1, 32])],None,56
-No: 4   GFLOPS: 1.85/11.85      result: MeasureResult(costs=(0.1450383722,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4459638595581055, timestamp=1659639720.0794039)       [(&#39;tile_y&#39;, [-1, 1]), (&#39;tile_x&#39;, [-1, 4])],None,20
-No: 5   GFLOPS: 3.70/11.85      result: MeasureResult(costs=(0.07249268680000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.292184591293335, timestamp=1659639721.5019739) [(&#39;tile_y&#39;, [-1, 256]), (&#39;tile_x&#39;, [-1, 16])],None,48
-No: 6   GFLOPS: 1.76/11.85      result: MeasureResult(costs=(0.1523721116,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.562816858291626, timestamp=1659639724.6312842)        [(&#39;tile_y&#39;, [-1, 512]), (&#39;tile_x&#39;, [-1, 4])],None,29
-No: 7   GFLOPS: 0.87/11.85      result: MeasureResult(costs=(0.30950368279999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.066531658172607, timestamp=1659639729.7433884) [(&#39;tile_y&#39;, [-1, 512]), (&#39;tile_x&#39;, [-1, 2])],None,19
-No: 8   GFLOPS: 10.52/11.85     result: MeasureResult(costs=(0.0255115052,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5481798648834229, timestamp=1659639730.3131433)       [(&#39;tile_y&#39;, [-1, 4]), (&#39;tile_x&#39;, [-1, 64])],None,62
-No: 9   GFLOPS: 1.60/11.85      result: MeasureResult(costs=(0.167932672,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.785961627960205, timestamp=1659639733.2173142) [(&#39;tile_y&#39;, [-1, 2]), (&#39;tile_x&#39;, [-1, 2])],None,11
-No: 10  GFLOPS: 2.77/11.85      result: MeasureResult(costs=(0.0970107032,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6561565399169922, timestamp=1659639734.9309878)       [(&#39;tile_y&#39;, [-1, 4]), (&#39;tile_x&#39;, [-1, 4])],None,22
+No: 1   GFLOPS: 11.54/11.54     result: MeasureResult(costs=(0.023254367800000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5027024745941162, timestamp=1659646522.1498861)       [(&#39;tile_y&#39;, [-1, 1]), (&#39;tile_x&#39;, [-1, 256])],None,80
+No: 2   GFLOPS: 2.99/11.54      result: MeasureResult(costs=(0.08978048320000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5882461071014404, timestamp=1659646523.7476647)        [(&#39;tile_y&#39;, [-1, 4]), (&#39;tile_x&#39;, [-1, 8])],None,32
+No: 3   GFLOPS: 12.01/12.01     result: MeasureResult(costs=(0.0223575308,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5568971633911133, timestamp=1659646524.7873862)       [(&#39;tile_y&#39;, [-1, 64]), (&#39;tile_x&#39;, [-1, 32])],None,56
+No: 4   GFLOPS: 1.80/12.01      result: MeasureResult(costs=(0.14952399,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.517800807952881, timestamp=1659646527.869588)   [(&#39;tile_y&#39;, [-1, 1]), (&#39;tile_x&#39;, [-1, 4])],None,20
+No: 5   GFLOPS: 3.72/12.01      result: MeasureResult(costs=(0.0720663812,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2833402156829834, timestamp=1659646529.280509)        [(&#39;tile_y&#39;, [-1, 256]), (&#39;tile_x&#39;, [-1, 16])],None,48
+No: 6   GFLOPS: 1.88/12.01      result: MeasureResult(costs=(0.1424236102,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4384822845458984, timestamp=1659646531.7613738)       [(&#39;tile_y&#39;, [-1, 512]), (&#39;tile_x&#39;, [-1, 4])],None,29
+No: 7   GFLOPS: 0.89/12.01      result: MeasureResult(costs=(0.3020184768,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.94750452041626, timestamp=1659646537.2712343) [(&#39;tile_y&#39;, [-1, 512]), (&#39;tile_x&#39;, [-1, 2])],None,19
+No: 8   GFLOPS: 10.82/12.01     result: MeasureResult(costs=(0.0247996618,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5380039215087891, timestamp=1659646537.828989)        [(&#39;tile_y&#39;, [-1, 4]), (&#39;tile_x&#39;, [-1, 64])],None,62
+No: 9   GFLOPS: 1.77/12.01      result: MeasureResult(costs=(0.1515593636,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.53814959526062, timestamp=1659646540.485943)  [(&#39;tile_y&#39;, [-1, 2]), (&#39;tile_x&#39;, [-1, 2])],None,11
+No: 10  GFLOPS: 2.82/12.01      result: MeasureResult(costs=(0.095165439,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.642676830291748, timestamp=1659646542.1685784) [(&#39;tile_y&#39;, [-1, 4]), (&#39;tile_x&#39;, [-1, 4])],None,22
 </pre></div>
 </div>
 <p>With tuning completed, we can choose the configuration from the log file that
diff --git a/docs/tutorial/autotvm_relay_x86.html b/docs/tutorial/autotvm_relay_x86.html
index d9acdc905..2290c32b5 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -550,7 +550,7 @@ standard deviation.</p>
 <span class="nb">print</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">unoptimized</span></a><span class="p">)</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{&#39;mean&#39;: 493.08102606999455, &#39;median&#39;: 492.9313444999707, &#39;std&#39;: 0.6852841328006576}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{&#39;mean&#39;: 492.7949012599993, &#39;median&#39;: 492.77268674999846, &#39;std&#39;: 0.5315715046600841}
 </pre></div>
 </div>
 </div>
@@ -705,178 +705,178 @@ depending on the specifics of the model and the target platform.</p>
   &quot;target_host parameter is going to be deprecated. &quot;
 
 [Task  1/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  1/25]  Current/Best:   17.56/  17.56 GFLOPS | Progress: (4/20) | 6.31 s
-[Task  1/25]  Current/Best:    6.17/  17.56 GFLOPS | Progress: (8/20) | 9.31 s
-[Task  1/25]  Current/Best:   11.57/  22.74 GFLOPS | Progress: (12/20) | 11.73 s
-[Task  1/25]  Current/Best:   16.92/  22.84 GFLOPS | Progress: (16/20) | 13.41 s
-[Task  1/25]  Current/Best:   11.60/  23.94 GFLOPS | Progress: (20/20) | 15.14 s Done.
+[Task  1/25]  Current/Best:   17.53/  17.53 GFLOPS | Progress: (4/20) | 6.26 s
+[Task  1/25]  Current/Best:    6.17/  17.53 GFLOPS | Progress: (8/20) | 9.25 s
+[Task  1/25]  Current/Best:   11.56/  22.70 GFLOPS | Progress: (12/20) | 11.70 s
+[Task  1/25]  Current/Best:   16.78/  22.86 GFLOPS | Progress: (16/20) | 13.39 s
+[Task  1/25]  Current/Best:   11.63/  23.90 GFLOPS | Progress: (20/20) | 15.14 s Done.
 
 [Task  2/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  2/25]  Current/Best:   12.12/  13.05 GFLOPS | Progress: (4/20) | 3.78 s
-[Task  2/25]  Current/Best:   14.16/  18.59 GFLOPS | Progress: (8/20) | 5.10 s
-[Task  2/25]  Current/Best:   21.01/  21.01 GFLOPS | Progress: (12/20) | 6.42 s
-[Task  2/25]  Current/Best:   12.40/  21.01 GFLOPS | Progress: (16/20) | 7.68 s
-[Task  2/25]  Current/Best:   19.27/  21.01 GFLOPS | Progress: (20/20) | 9.28 s Done.
+[Task  2/25]  Current/Best:   12.37/  13.20 GFLOPS | Progress: (4/20) | 3.76 s
+[Task  2/25]  Current/Best:   14.22/  18.95 GFLOPS | Progress: (8/20) | 5.07 s
+[Task  2/25]  Current/Best:   21.19/  21.19 GFLOPS | Progress: (12/20) | 6.38 s
+[Task  2/25]  Current/Best:   12.47/  21.19 GFLOPS | Progress: (16/20) | 7.67 s
+[Task  2/25]  Current/Best:   19.38/  21.19 GFLOPS | Progress: (20/20) | 9.28 s Done.
 
 [Task  3/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  3/25]  Current/Best:    1.63/  10.53 GFLOPS | Progress: (4/20) | 5.87 s
-[Task  3/25]  Current/Best:   15.60/  16.85 GFLOPS | Progress: (8/20) | 7.80 s
-[Task  3/25]  Current/Best:   14.89/  16.85 GFLOPS | Progress: (12/20) | 9.54 s
-[Task  3/25]  Current/Best:    7.20/  23.79 GFLOPS | Progress: (16/20) | 11.47 s
-[Task  3/25]  Current/Best:   12.66/  23.79 GFLOPS | Progress: (20/20) | 15.97 s Done.
+[Task  3/25]  Current/Best:    1.63/  10.58 GFLOPS | Progress: (4/20) | 5.87 s
+[Task  3/25]  Current/Best:   15.46/  16.86 GFLOPS | Progress: (8/20) | 7.81 s
+[Task  3/25]  Current/Best:   14.87/  16.86 GFLOPS | Progress: (12/20) | 9.51 s
+[Task  3/25]  Current/Best:    7.20/  23.82 GFLOPS | Progress: (16/20) | 11.42 s
+[Task  3/25]  Current/Best:   11.74/  23.82 GFLOPS | Progress: (20/20) | 15.97 s Done.
 
 [Task  4/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  4/25]  Current/Best:    9.56/  20.57 GFLOPS | Progress: (4/20) | 2.38 s
-[Task  4/25]  Current/Best:    6.86/  20.57 GFLOPS | Progress: (8/20) | 6.68 s
-[Task  4/25]  Current/Best:   22.32/  22.32 GFLOPS | Progress: (12/20) | 11.10 s
-[Task  4/25]  Current/Best:   17.47/  22.32 GFLOPS | Progress: (16/20) | 13.35 s
-[Task  4/25]  Current/Best:   13.54/  22.32 GFLOPS | Progress: (20/20) | 15.32 s Done.
+[Task  4/25]  Current/Best:    9.57/  20.42 GFLOPS | Progress: (4/20) | 2.38 s
+[Task  4/25]  Current/Best:    6.86/  20.42 GFLOPS | Progress: (8/20) | 7.06 s
+[Task  4/25]  Current/Best:   22.49/  22.49 GFLOPS | Progress: (12/20) | 12.04 s
+[Task  4/25]  Current/Best:   17.26/  22.49 GFLOPS | Progress: (16/20) | 14.41 s
+[Task  4/25]  Current/Best:   13.29/  22.49 GFLOPS | Progress: (20/20) | 16.49 s Done.
 
 [Task  5/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  5/25]  Current/Best:    9.51/  10.30 GFLOPS | Progress: (4/20) | 2.59 s
-[Task  5/25]  Current/Best:   11.68/  12.41 GFLOPS | Progress: (8/20) | 4.66 s
-[Task  5/25]  Current/Best:   11.58/  17.99 GFLOPS | Progress: (12/20) | 7.59 s
-[Task  5/25]  Current/Best:   11.64/  22.64 GFLOPS | Progress: (16/20) | 9.01 s
-[Task  5/25]  Current/Best:   11.96/  22.64 GFLOPS | Progress: (20/20) | 10.87 s Done.
+[Task  5/25]  Current/Best:    9.77/  10.44 GFLOPS | Progress: (4/20) | 2.58 s
+[Task  5/25]  Current/Best:   11.84/  12.75 GFLOPS | Progress: (8/20) | 4.64 s
+[Task  5/25]  Current/Best:   11.48/  17.98 GFLOPS | Progress: (12/20) | 7.85 s
+[Task  5/25]  Current/Best:   11.89/  22.87 GFLOPS | Progress: (16/20) | 9.27 s
+[Task  5/25]  Current/Best:   12.04/  22.87 GFLOPS | Progress: (20/20) | 11.20 s Done.
 
 [Task  6/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  6/25]  Current/Best:   12.27/  20.77 GFLOPS | Progress: (4/20) | 3.98 s
-[Task  6/25]  Current/Best:   17.51/  20.77 GFLOPS | Progress: (8/20) | 5.75 s
-[Task  6/25]  Current/Best:   13.31/  20.77 GFLOPS | Progress: (12/20) | 7.68 s
-[Task  6/25]  Current/Best:   20.01/  20.77 GFLOPS | Progress: (16/20) | 9.96 s
-[Task  6/25]  Current/Best:    3.72/  20.77 GFLOPS | Progress: (20/20) | 12.50 s Done.
+[Task  6/25]  Current/Best:   12.29/  20.66 GFLOPS | Progress: (4/20) | 4.10 s
+[Task  6/25]  Current/Best:   19.13/  20.66 GFLOPS | Progress: (8/20) | 5.87 s
+[Task  6/25]  Current/Best:   13.18/  20.66 GFLOPS | Progress: (12/20) | 7.82 s
+[Task  6/25]  Current/Best:   20.04/  20.66 GFLOPS | Progress: (16/20) | 10.05 s
+[Task  6/25]  Current/Best:    3.74/  20.66 GFLOPS | Progress: (20/20) | 12.59 s Done.
 
 [Task  7/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  7/25]  Current/Best:   11.23/  12.88 GFLOPS | Progress: (4/20) | 3.61 s
-[Task  7/25]  Current/Best:   20.26/  21.07 GFLOPS | Progress: (8/20) | 5.12 s
-[Task  7/25]  Current/Best:   16.11/  21.07 GFLOPS | Progress: (12/20) | 7.05 s
-[Task  7/25]  Current/Best:   12.27/  21.07 GFLOPS | Progress: (16/20) | 9.10 s
-[Task  7/25]  Current/Best:    6.44/  21.80 GFLOPS | Progress: (20/20) | 11.55 s Done.
+[Task  7/25]  Current/Best:    9.84/  12.96 GFLOPS | Progress: (4/20) | 3.64 s
+[Task  7/25]  Current/Best:   20.34/  21.05 GFLOPS | Progress: (8/20) | 5.15 s
+[Task  7/25]  Current/Best:   15.91/  21.05 GFLOPS | Progress: (12/20) | 7.05 s
+[Task  7/25]  Current/Best:   12.29/  21.05 GFLOPS | Progress: (16/20) | 9.08 s
+[Task  7/25]  Current/Best:    6.32/  21.74 GFLOPS | Progress: (20/20) | 11.53 s Done.
 
 [Task  8/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  8/25]  Current/Best:    9.71/  13.70 GFLOPS | Progress: (4/20) | 2.91 s
-[Task  8/25]  Current/Best:    9.17/  13.70 GFLOPS | Progress: (8/20) | 7.62 s
-[Task  8/25]  Current/Best:   12.73/  13.70 GFLOPS | Progress: (12/20) | 13.71 s
-[Task  8/25]  Current/Best:   18.68/  18.68 GFLOPS | Progress: (16/20) | 15.80 s
-[Task  8/25]  Current/Best:   19.84/  19.84 GFLOPS | Progress: (20/20) | 22.27 s Done.
+[Task  8/25]  Current/Best:    9.97/  14.12 GFLOPS | Progress: (4/20) | 2.92 s
+[Task  8/25]  Current/Best:    9.47/  14.12 GFLOPS | Progress: (8/20) | 7.95 s
+[Task  8/25]  Current/Best:   12.70/  14.12 GFLOPS | Progress: (12/20) | 14.36 s
+[Task  8/25]  Current/Best:   18.82/  18.82 GFLOPS | Progress: (16/20) | 16.46 s
+[Task  8/25]  Current/Best:   20.04/  20.04 GFLOPS | Progress: (20/20) | 23.53 s Done.
 
 [Task  9/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  9/25]  Current/Best:   14.34/  15.74 GFLOPS | Progress: (4/20) | 11.95 s
-[Task  9/25]  Current/Best:   23.43/  23.43 GFLOPS | Progress: (8/20) | 13.80 s
-[Task  9/25]  Current/Best:    8.24/  23.43 GFLOPS | Progress: (12/20) | 16.16 s
-[Task  9/25]  Current/Best:   18.06/  23.43 GFLOPS | Progress: (16/20) | 18.72 s
-[Task  9/25]  Current/Best:    9.24/  23.43 GFLOPS | Progress: (20/20) | 26.39 s
+[Task  9/25]  Current/Best:   14.38/  15.72 GFLOPS | Progress: (4/20) | 11.96 s
+[Task  9/25]  Current/Best:   23.54/  23.54 GFLOPS | Progress: (8/20) | 13.71 s
+[Task  9/25]  Current/Best:    8.28/  23.54 GFLOPS | Progress: (12/20) | 16.24 s
+[Task  9/25]  Current/Best:   18.01/  23.54 GFLOPS | Progress: (16/20) | 19.08 s
+[Task  9/25]  Current/Best:    9.24/  23.54 GFLOPS | Progress: (20/20) | 27.60 s
 [Task 10/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25]  Current/Best:   18.18/  18.18 GFLOPS | Progress: (4/20) | 2.57 s
-[Task 10/25]  Current/Best:   15.57/  18.18 GFLOPS | Progress: (8/20) | 4.15 s
-[Task 10/25]  Current/Best:   12.33/  18.92 GFLOPS | Progress: (12/20) | 5.67 s
-[Task 10/25]  Current/Best:   18.98/  20.15 GFLOPS | Progress: (16/20) | 6.79 s
-[Task 10/25]  Current/Best:    8.85/  20.15 GFLOPS | Progress: (20/20) | 8.34 s Done.
+[Task 10/25]  Current/Best:   18.16/  18.16 GFLOPS | Progress: (4/20) | 2.54 s
+[Task 10/25]  Current/Best:   15.49/  18.16 GFLOPS | Progress: (8/20) | 4.17 s
+[Task 10/25]  Current/Best:   12.54/  18.95 GFLOPS | Progress: (12/20) | 5.71 s
+[Task 10/25]  Current/Best:   19.14/  20.38 GFLOPS | Progress: (16/20) | 6.82 s
+[Task 10/25]  Current/Best:    8.92/  20.38 GFLOPS | Progress: (20/20) | 8.37 s Done.
 
 [Task 11/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25]  Current/Best:   12.28/  18.15 GFLOPS | Progress: (4/20) | 3.26 s
-[Task 11/25]  Current/Best:   14.87/  18.15 GFLOPS | Progress: (8/20) | 6.03 s
-[Task 11/25]  Current/Best:   18.17/  18.17 GFLOPS | Progress: (12/20) | 8.10 s
-[Task 11/25]  Current/Best:   13.52/  21.23 GFLOPS | Progress: (16/20) | 10.81 s
-[Task 11/25]  Current/Best:   19.41/  21.62 GFLOPS | Progress: (20/20) | 12.81 s Done.
+[Task 11/25]  Current/Best:   12.34/  18.12 GFLOPS | Progress: (4/20) | 3.31 s
+[Task 11/25]  Current/Best:   16.92/  18.12 GFLOPS | Progress: (8/20) | 6.10 s
+[Task 11/25]  Current/Best:   16.54/  18.12 GFLOPS | Progress: (12/20) | 8.14 s
+[Task 11/25]  Current/Best:   13.36/  21.22 GFLOPS | Progress: (16/20) | 11.09 s
+[Task 11/25]  Current/Best:   19.43/  21.62 GFLOPS | Progress: (20/20) | 13.15 s Done.
 
 [Task 12/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25]  Current/Best:    7.82/  18.15 GFLOPS | Progress: (4/20) | 5.34 s
-[Task 12/25]  Current/Best:    5.18/  18.15 GFLOPS | Progress: (8/20) | 9.05 s
-[Task 12/25]  Current/Best:   18.86/  18.88 GFLOPS | Progress: (12/20) | 11.03 s
-[Task 12/25]  Current/Best:   15.44/  18.88 GFLOPS | Progress: (16/20) | 13.82 s
-[Task 12/25]  Current/Best:   15.12/  18.88 GFLOPS | Progress: (20/20) | 15.73 s Done.
+[Task 12/25]  Current/Best:    7.83/  18.27 GFLOPS | Progress: (4/20) | 5.70 s
+[Task 12/25]  Current/Best:    5.26/  18.27 GFLOPS | Progress: (8/20) | 9.58 s
+[Task 12/25]  Current/Best:   19.04/  19.04 GFLOPS | Progress: (12/20) | 11.56 s
+[Task 12/25]  Current/Best:   15.54/  19.04 GFLOPS | Progress: (16/20) | 14.46 s
+[Task 12/25]  Current/Best:   15.16/  19.04 GFLOPS | Progress: (20/20) | 16.37 s Done.
 
 [Task 13/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25]  Current/Best:    8.92/  17.29 GFLOPS | Progress: (4/20) | 3.65 s
-[Task 13/25]  Current/Best:   15.73/  20.98 GFLOPS | Progress: (8/20) | 6.08 s
-[Task 13/25]  Current/Best:   19.61/  21.75 GFLOPS | Progress: (12/20) | 8.93 s
-[Task 13/25]  Current/Best:   12.26/  21.75 GFLOPS | Progress: (16/20) | 12.35 s
-[Task 13/25]  Current/Best:   18.58/  21.75 GFLOPS | Progress: (20/20) | 14.62 s Done.
+[Task 13/25]  Current/Best:    8.76/  17.32 GFLOPS | Progress: (4/20) | 3.75 s
+[Task 13/25]  Current/Best:   16.14/  20.92 GFLOPS | Progress: (8/20) | 6.34 s
+[Task 13/25]  Current/Best:   19.54/  21.34 GFLOPS | Progress: (12/20) | 9.45 s
+[Task 13/25]  Current/Best:   12.22/  21.34 GFLOPS | Progress: (16/20) | 12.89 s
+[Task 13/25]  Current/Best:   18.96/  21.34 GFLOPS | Progress: (20/20) | 15.22 s Done.
 
 [Task 14/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25]  Current/Best:   12.03/  13.29 GFLOPS | Progress: (4/20) | 3.36 s
-[Task 14/25]  Current/Best:    6.09/  13.39 GFLOPS | Progress: (8/20) | 5.55 s
-[Task 14/25]  Current/Best:   20.70/  20.70 GFLOPS | Progress: (12/20) | 8.07 s
-[Task 14/25]  Current/Best:   16.28/  20.70 GFLOPS | Progress: (16/20) | 9.72 s Done.
+[Task 14/25]  Current/Best:   13.65/  13.65 GFLOPS | Progress: (4/20) | 3.42 s
+[Task 14/25]  Current/Best:    6.12/  13.65 GFLOPS | Progress: (8/20) | 5.61 s
+[Task 14/25]  Current/Best:   19.94/  19.94 GFLOPS | Progress: (12/20) | 8.25 s
+[Task 14/25]  Current/Best:   16.43/  19.94 GFLOPS | Progress: (16/20) | 9.90 s Done.
 
-[Task 14/25]  Current/Best:   17.56/  20.70 GFLOPS | Progress: (20/20) | 11.52 s
+[Task 14/25]  Current/Best:   17.33/  19.94 GFLOPS | Progress: (20/20) | 11.66 s
 [Task 15/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25]  Current/Best:   16.16/  17.66 GFLOPS | Progress: (4/20) | 2.70 s
-[Task 15/25]  Current/Best:   14.53/  18.04 GFLOPS | Progress: (8/20) | 4.05 s
-[Task 15/25]  Current/Best:   10.39/  22.29 GFLOPS | Progress: (12/20) | 6.10 s
-[Task 15/25]  Current/Best:   20.43/  22.29 GFLOPS | Progress: (16/20) | 9.43 s
-[Task 15/25]  Current/Best:    9.63/  22.29 GFLOPS | Progress: (20/20) | 10.45 s
+[Task 15/25]  Current/Best:   16.17/  17.66 GFLOPS | Progress: (4/20) | 2.71 s
+[Task 15/25]  Current/Best:   13.07/  18.06 GFLOPS | Progress: (8/20) | 4.07 s
+[Task 15/25]  Current/Best:   10.41/  22.34 GFLOPS | Progress: (12/20) | 6.28 s
+[Task 15/25]  Current/Best:   20.40/  22.34 GFLOPS | Progress: (16/20) | 9.34 s
+[Task 15/25]  Current/Best:    9.66/  22.34 GFLOPS | Progress: (20/20) | 10.36 s
 [Task 16/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25]  Current/Best:   20.36/  20.36 GFLOPS | Progress: (4/20) | 2.98 s
-[Task 16/25]  Current/Best:    3.04/  20.36 GFLOPS | Progress: (8/20) | 4.59 s
-[Task 16/25]  Current/Best:   19.38/  20.36 GFLOPS | Progress: (12/20) | 5.79 s
-[Task 16/25]  Current/Best:   17.96/  20.36 GFLOPS | Progress: (16/20) | 7.14 s
-[Task 16/25]  Current/Best:   10.03/  21.12 GFLOPS | Progress: (20/20) | 9.19 s Done.
+[Task 16/25]  Current/Best:   20.39/  20.39 GFLOPS | Progress: (4/20) | 2.95 s
+[Task 16/25]  Current/Best:    3.04/  20.39 GFLOPS | Progress: (8/20) | 4.55 s
+[Task 16/25]  Current/Best:   19.54/  20.39 GFLOPS | Progress: (12/20) | 5.75 s
+[Task 16/25]  Current/Best:   17.97/  20.39 GFLOPS | Progress: (16/20) | 7.12 s
+[Task 16/25]  Current/Best:   10.04/  22.32 GFLOPS | Progress: (20/20) | 9.26 s Done.
 
 [Task 17/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25]  Current/Best:   13.23/  18.70 GFLOPS | Progress: (4/20) | 4.69 s
-[Task 17/25]  Current/Best:   13.92/  23.42 GFLOPS | Progress: (8/20) | 7.54 s
-[Task 17/25]  Current/Best:   16.87/  23.42 GFLOPS | Progress: (12/20) | 9.60 s
-[Task 17/25]  Current/Best:   16.58/  23.42 GFLOPS | Progress: (16/20) | 11.73 s
-[Task 17/25]  Current/Best:   10.05/  23.42 GFLOPS | Progress: (20/20) | 13.83 s Done.
+[Task 17/25]  Current/Best:   13.17/  17.01 GFLOPS | Progress: (4/20) | 4.79 s
+[Task 17/25]  Current/Best:   14.33/  23.27 GFLOPS | Progress: (8/20) | 7.70 s
+[Task 17/25]  Current/Best:   16.86/  23.27 GFLOPS | Progress: (12/20) | 9.76 s
+[Task 17/25]  Current/Best:   16.43/  23.27 GFLOPS | Progress: (16/20) | 11.96 s
+[Task 17/25]  Current/Best:   10.05/  23.27 GFLOPS | Progress: (20/20) | 14.11 s Done.
 
 [Task 18/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25]  Current/Best:   11.24/  17.03 GFLOPS | Progress: (4/20) | 3.69 s
-[Task 18/25]  Current/Best:   10.53/  19.56 GFLOPS | Progress: (8/20) | 7.09 s
-[Task 18/25]  Current/Best:   19.50/  19.56 GFLOPS | Progress: (12/20) | 9.04 s
-[Task 18/25]  Current/Best:   10.06/  19.56 GFLOPS | Progress: (16/20) | 12.58 s
-[Task 18/25]  Current/Best:   20.64/  20.64 GFLOPS | Progress: (20/20) | 14.07 s Done.
+[Task 18/25]  Current/Best:   11.33/  18.22 GFLOPS | Progress: (4/20) | 3.79 s
+[Task 18/25]  Current/Best:   10.57/  18.22 GFLOPS | Progress: (8/20) | 7.44 s
+[Task 18/25]  Current/Best:   18.77/  18.77 GFLOPS | Progress: (12/20) | 9.37 s
+[Task 18/25]  Current/Best:    9.98/  18.77 GFLOPS | Progress: (16/20) | 13.26 s
+[Task 18/25]  Current/Best:   20.57/  20.57 GFLOPS | Progress: (20/20) | 14.76 s Done.
 
 [Task 19/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25]  Current/Best:    7.05/  20.37 GFLOPS | Progress: (4/20) | 6.01 s
-[Task 19/25]  Current/Best:    2.60/  20.37 GFLOPS | Progress: (8/20) | 9.24 s
-[Task 19/25]  Current/Best:   19.40/  21.75 GFLOPS | Progress: (12/20) | 12.06 s
-[Task 19/25]  Current/Best:   14.20/  21.75 GFLOPS | Progress: (16/20) | 14.92 s
-[Task 19/25]  Current/Best:    2.70/  23.53 GFLOPS | Progress: (20/20) | 17.72 s Done.
+[Task 19/25]  Current/Best:    6.90/  20.48 GFLOPS | Progress: (4/20) | 6.11 s
+[Task 19/25]  Current/Best:    2.61/  20.48 GFLOPS | Progress: (8/20) | 9.43 s
+[Task 19/25]  Current/Best:   19.83/  21.37 GFLOPS | Progress: (12/20) | 12.33 s
+[Task 19/25]  Current/Best:   14.10/  21.52 GFLOPS | Progress: (16/20) | 15.31 s
+[Task 19/25]  Current/Best:    2.70/  23.68 GFLOPS | Progress: (20/20) | 18.07 s Done.
 
 [Task 20/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25]  Current/Best:    9.01/  15.07 GFLOPS | Progress: (4/20) | 3.34 s Done.
+[Task 20/25]  Current/Best:    9.01/  15.30 GFLOPS | Progress: (4/20) | 3.31 s Done.
  Done.
 
-[Task 20/25]  Current/Best:    9.79/  15.07 GFLOPS | Progress: (8/20) | 6.62 s
-[Task 20/25]  Current/Best:    2.32/  16.70 GFLOPS | Progress: (12/20) | 10.52 s
-[Task 20/25]  Current/Best:   12.51/  16.70 GFLOPS | Progress: (16/20) | 14.23 s
-[Task 20/25]  Current/Best:   13.56/  22.32 GFLOPS | Progress: (20/20) | 16.28 s
+[Task 20/25]  Current/Best:    9.79/  15.30 GFLOPS | Progress: (8/20) | 6.74 s
+[Task 20/25]  Current/Best:    2.32/  16.89 GFLOPS | Progress: (12/20) | 10.61 s
+[Task 20/25]  Current/Best:   12.58/  16.89 GFLOPS | Progress: (16/20) | 14.31 s
+[Task 20/25]  Current/Best:   11.79/  22.00 GFLOPS | Progress: (20/20) | 16.41 s
 [Task 21/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25]  Current/Best:    6.40/  17.71 GFLOPS | Progress: (4/20) | 3.22 s
-[Task 21/25]  Current/Best:   14.63/  17.71 GFLOPS | Progress: (8/20) | 4.78 s
-[Task 21/25]  Current/Best:    1.61/  17.71 GFLOPS | Progress: (12/20) | 6.94 s
-[Task 21/25]  Current/Best:   18.06/  18.06 GFLOPS | Progress: (16/20) | 10.36 s
-[Task 21/25]  Current/Best:    4.47/  18.06 GFLOPS | Progress: (20/20) | 17.47 s
+[Task 21/25]  Current/Best:    6.40/  17.74 GFLOPS | Progress: (4/20) | 3.27 s
+[Task 21/25]  Current/Best:   14.66/  17.74 GFLOPS | Progress: (8/20) | 4.86 s
+[Task 21/25]  Current/Best:    1.61/  17.74 GFLOPS | Progress: (12/20) | 7.01 s
+[Task 21/25]  Current/Best:   17.84/  17.84 GFLOPS | Progress: (16/20) | 10.54 s
+[Task 21/25]  Current/Best:    4.47/  17.84 GFLOPS | Progress: (20/20) | 17.81 s
 [Task 22/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25]  Current/Best:    2.70/  17.03 GFLOPS | Progress: (4/20) | 2.67 s
-[Task 22/25]  Current/Best:    8.60/  22.06 GFLOPS | Progress: (8/20) | 4.57 s
-[Task 22/25]  Current/Best:   19.76/  22.06 GFLOPS | Progress: (12/20) | 6.89 s
-[Task 22/25]  Current/Best:   15.05/  22.06 GFLOPS | Progress: (16/20) | 8.91 s
-[Task 22/25]  Current/Best:   14.11/  22.06 GFLOPS | Progress: (20/20) | 10.63 s Done.
+[Task 22/25]  Current/Best:    2.70/  17.01 GFLOPS | Progress: (4/20) | 2.67 s
+[Task 22/25]  Current/Best:    8.70/  22.02 GFLOPS | Progress: (8/20) | 4.65 s
+[Task 22/25]  Current/Best:   19.56/  22.02 GFLOPS | Progress: (12/20) | 7.04 s
+[Task 22/25]  Current/Best:   15.44/  22.02 GFLOPS | Progress: (16/20) | 9.17 s
+[Task 22/25]  Current/Best:   14.63/  22.02 GFLOPS | Progress: (20/20) | 10.89 s Done.
 
 [Task 23/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25]  Current/Best:   17.59/  20.78 GFLOPS | Progress: (4/20) | 3.26 s
-[Task 23/25]  Current/Best:   14.65/  20.78 GFLOPS | Progress: (8/20) | 6.62 s
-[Task 23/25]  Current/Best:   20.73/  21.77 GFLOPS | Progress: (12/20) | 8.41 s
-[Task 23/25]  Current/Best:    6.29/  21.77 GFLOPS | Progress: (16/20) | 15.52 s
-[Task 23/25]  Current/Best:    7.82/  21.77 GFLOPS | Progress: (20/20) | 19.71 s Done.
+[Task 23/25]  Current/Best:   17.70/  20.94 GFLOPS | Progress: (4/20) | 3.28 s
+[Task 23/25]  Current/Best:   14.57/  20.94 GFLOPS | Progress: (8/20) | 6.74 s
+[Task 23/25]  Current/Best:   21.32/  21.32 GFLOPS | Progress: (12/20) | 8.55 s
+[Task 23/25]  Current/Best:    6.57/  21.32 GFLOPS | Progress: (16/20) | 15.56 s
+[Task 23/25]  Current/Best:    8.15/  21.32 GFLOPS | Progress: (20/20) | 19.69 s Done.
 
 [Task 24/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25]  Current/Best:    8.36/   8.36 GFLOPS | Progress: (4/20) | 11.80 s
-[Task 24/25]  Current/Best:    2.15/   8.36 GFLOPS | Progress: (8/20) | 22.85 s
-[Task 24/25]  Current/Best:    4.28/   8.36 GFLOPS | Progress: (12/20) | 34.37 s Done.
+[Task 24/25]  Current/Best:    8.94/   8.94 GFLOPS | Progress: (4/20) | 11.79 s
+[Task 24/25]  Current/Best:    2.15/   8.94 GFLOPS | Progress: (8/20) | 22.77 s
+[Task 24/25]  Current/Best:    4.57/   8.94 GFLOPS | Progress: (12/20) | 34.27 s Done.
 
-[Task 24/25]  Current/Best:    5.93/   8.65 GFLOPS | Progress: (16/20) | 39.69 s
-[Task 24/25]  Current/Best:    3.34/   8.79 GFLOPS | Progress: (20/20) | 45.65 s Done.
+[Task 24/25]  Current/Best:    6.38/   8.94 GFLOPS | Progress: (16/20) | 39.91 s
+[Task 24/25]  Current/Best:    3.44/   8.94 GFLOPS | Progress: (20/20) | 45.80 s Done.
 
 [Task 25/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 25/25]  Current/Best:    1.55/   2.79 GFLOPS | Progress: (4/20) | 11.61 s
-[Task 25/25]  Current/Best:    5.68/   7.76 GFLOPS | Progress: (8/20) | 22.85 s
-[Task 25/25]  Current/Best:    5.96/   7.76 GFLOPS | Progress: (12/20) | 34.12 s
-[Task 25/25]  Current/Best:    5.81/   8.98 GFLOPS | Progress: (16/20) | 35.85 s
-[Task 25/25]  Current/Best:    2.83/   9.15 GFLOPS | Progress: (20/20) | 46.51 s
+[Task 25/25]  Current/Best:    1.57/   2.95 GFLOPS | Progress: (4/20) | 11.58 s
+[Task 25/25]  Current/Best:    5.90/   8.45 GFLOPS | Progress: (8/20) | 22.85 s
+[Task 25/25]  Current/Best:    5.95/   8.45 GFLOPS | Progress: (12/20) | 34.23 s
+[Task 25/25]  Current/Best:    5.84/   9.39 GFLOPS | Progress: (16/20) | 35.94 s
+[Task 25/25]  Current/Best:    2.92/   9.39 GFLOPS | Progress: (20/20) | 46.62 s
 </pre></div>
 </div>
 <p>The output from this tuning process will look something like this:</p>
@@ -980,8 +980,8 @@ improvement in comparing the optimized model to the unoptimized model.</p>
 <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;unoptimized: </span><span class="si">%s</span><span class="s2">&quot;</span> <span class="o">%</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">unoptimized</span></a><span class="p">))</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {&#39;mean&#39;: 409.60669237000275, &#39;median&#39;: 408.862635950004, &#39;std&#39;: 1.8723862551091004}
-unoptimized: {&#39;mean&#39;: 493.08102606999455, &#39;median&#39;: 492.9313444999707, &#39;std&#39;: 0.6852841328006576}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {&#39;mean&#39;: 397.1788065399983, &#39;median&#39;: 396.51443220000147, &#39;std&#39;: 1.663312213932835}
+unoptimized: {&#39;mean&#39;: 492.7949012599993, &#39;median&#39;: 492.77268674999846, &#39;std&#39;: 0.5315715046600841}
 </pre></div>
 </div>
 </div>
@@ -995,7 +995,7 @@ models.</p>
 <p>Here we presented a simple example using ResNet-50 v2 locally. However, TVM
 supports many more features including cross-compilation, remote execution and
 profiling/benchmarking.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes  14.369 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes  23.040 seconds)</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-autotvm-relay-x86-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../_downloads/57a45d9bef1af358191e7d50043e652c/autotvm_relay_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">autotvm_relay_x86.py</span></code></a></p>
diff --git a/docs/tutorial/cross_compilation_and_rpc.html b/docs/tutorial/cross_compilation_and_rpc.html
index 8da5df63f..975abe975 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -526,7 +526,7 @@ device and returns the measured cost. Network overhead is excluded.</p>
 <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;</span><span class="si">%g</span><span class="s2"> secs/op&quot;</span> <span class="o">%</span> <span class="n">cost</span><span class="p">)</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.458e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.201e-07 secs/op
 </pre></div>
 </div>
 </div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index f6dd8c046..7f62b621d 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -483,7 +483,7 @@ we can schedule the following series of operations ending with <code class="code
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sg</span><span class="o">.</span><span class="n">stages</span></a><span class="p">)</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x22cc11a0)), stage(b, placeholder(b, 0xc96ada0)), 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=[i [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0xd9b38e0)), stage(b, placeholder(b, 0x225481b0)), 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=[i [...]
 </pre></div>
 </div>
 <p>We can test the correctness by comparing with <code class="code docutils literal notranslate"><span class="pre">numpy</span></code> result as follows</p>
diff --git a/docs/tutorial/sg_execution_times.html b/docs/tutorial/sg_execution_times.html
index b0887a0b6..efcb045d6 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -327,7 +327,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-tutorial-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>13:07.745</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>13:07.833</strong> total execution time for <strong>tutorial</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 83%" />
@@ -336,42 +336,42 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="autotvm_relay_x86.html#sphx-glr-tutorial-autotvm-relay-x86-py"><span class="std std-ref">Compiling and Optimizing a Model with the Python Interface (AutoTVM)</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_relay_x86.py</span></code>)</p></td>
-<td><p>10:14.369</p></td>
+<td><p>10:23.040</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="tensor_expr_get_started.html#sphx-glr-tutorial-tensor-expr-get-started-py"><span class="std std-ref">Working with Operators Using Tensor Expression</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_expr_get_started.py</span></code>)</p></td>
-<td><p>01:01.065</p></td>
+<td><p>00:58.748</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="auto_scheduler_matmul_x86.html#sphx-glr-tutorial-auto-scheduler-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Auto-scheduling</span></a> (<code class="docutils literal notranslate"><span class="pre">auto_scheduler_matmul_x86.py</span></code>)</p></td>
-<td><p>00:56.530</p></td>
+<td><p>00:50.870</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="relay_quick_start.html#sphx-glr-tutorial-relay-quick-start-py"><span class="std std-ref">Quick Start Tutorial for Compiling Deep Learning Models</span></a> (<code class="docutils literal notranslate"><span class="pre">relay_quick_start.py</span></code>)</p></td>
-<td><p>00:30.210</p></td>
+<td><p>00:29.757</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="autotvm_matmul_x86.html#sphx-glr-tutorial-autotvm-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Schedule Templates and AutoTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_matmul_x86.py</span></code>)</p></td>
-<td><p>00:24.234</p></td>
+<td><p>00:23.421</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
-<tr class="row-even"><td><p><a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></td>
-<td><p>00:00.691</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></td>
+<td><p>00:01.154</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></td>
-<td><p>00:00.499</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></td>
+<td><p>00:00.692</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="cross_compilation_and_rpc.html#sphx-glr-tutorial-cross-compilation-and-rpc-py"><span class="std std-ref">Cross Compilation and RPC</span></a> (<code class="docutils literal notranslate"><span class="pre">cross_compilation_and_rpc.py</span></code>)</p></td>
-<td><p>00:00.141</p></td>
+<td><p>00:00.144</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="introduction.html#sphx-glr-tutorial-introduction-py"><span class="std std-ref">Introduction</span></a> (<code class="docutils literal notranslate"><span class="pre">introduction.py</span></code>)</p></td>
 <td><p>00:00.005</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
-<tr class="row-even"><td><p><a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="install.html#sphx-glr-tutorial-install-py"><span class="std std-ref">Installing TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">install.py</span></code>)</p></td>
 <td><p>00:00.001</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
@@ -379,7 +379,7 @@
 <td><p>00:00.001</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
-<tr class="row-even"><td><p><a class="reference internal" href="install.html#sphx-glr-tutorial-install-py"><span class="std std-ref">Installing TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">install.py</span></code>)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></td>
 <td><p>00:00.001</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index 21736d0c1..50066f4b6 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -541,8 +541,8 @@ helper function to run a profile of the TVM generated code.</p>
 <span class="n">evaluate_addition</span><span class="p">(</span><span class="n">fadd</span><span class="p">,</span> <a href="../reference/api/python/target.html#tvm.target.Target" title="tvm.target.Target" class="sphx-glr-backref-module-tvm-target sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">tgt</span></a><span class="p">,</span> <span class="s2">&quot;naive&quot;</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#list" ti [...]
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000008
-naive: 0.000009
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000007
+naive: 0.000006
 </pre></div>
 </div>
 </div>
@@ -593,7 +593,7 @@ compile and run this new schedule with the parallel operation applied:</p>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
   &quot;target_host parameter is going to be deprecated. &quot;
-parallel: 0.000009
+parallel: 0.000006
 </pre></div>
 </div>
 </div>
@@ -634,7 +634,7 @@ factor to be the number of threads on your CPU.</p>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
   &quot;target_host parameter is going to be deprecated. &quot;
-vector: 0.000025
+vector: 0.000024
 @main = primfn(A_1: handle, B_1: handle, C_1: handle) -&gt; ()
   attr = {&quot;from_legacy_te_schedule&quot;: True, &quot;global_symbol&quot;: &quot;main&quot;, &quot;tir.noalias&quot;: True}
   buffers = {A: Buffer(A_2: Pointer(float32), float32, [(stride: int32*n: int32)], [], type=&quot;auto&quot;),
@@ -667,10 +667,10 @@ vector: 0.000025
 </pre></div>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator                  Timing             Performance
-   numpy    7.506309998461802e-06                    1.0
-   naive    9.239200000000001e-06     1.2308577719136706
-parallel              8.8606e-06      1.1804202067081855
-  vector    2.4591400000000003e-05     3.276097044358585
+   numpy    6.9266200011952605e-06                   1.0
+   naive              5.8348e-06      0.8423733363448759
+parallel              5.8559e-06      0.8454195551350447
+  vector    2.3856499999999998e-05    3.4441762354342105
 </pre></div>
 </div>
 <div class="admonition-code-specialization admonition">
@@ -986,7 +986,7 @@ matrix multiplication.</p>
 <span class="n">answer</span> <span class="o">=</span> <span class="n">numpy</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">a</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">b</span><span class="o">.</span><span class="n">numpy</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: 0.018192
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.016793
 </pre></div>
 </div>
 <p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -1029,7 +1029,7 @@ optimizations.</p>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
   &quot;target_host parameter is going to be deprecated. &quot;
-none: 3.449567
+none: 3.291345
 </pre></div>
 </div>
 <p>Let’s take a look at the intermediate representation of the operator and
@@ -1096,7 +1096,7 @@ schedule.</p>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
   &quot;target_host parameter is going to be deprecated. &quot;
-blocking: 0.286718
+blocking: 0.294843
 </pre></div>
 </div>
 <p>By reordering the computation to take advantage of caching, you should see a
@@ -1157,7 +1157,7 @@ already cache friendly from our previous optimizations.</p>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
   &quot;target_host parameter is going to be deprecated. &quot;
-vectorization: 0.330775
+vectorization: 0.334288
 @main = primfn(A_1: handle, B_1: handle, C_1: handle) -&gt; ()
   attr = {&quot;from_legacy_te_schedule&quot;: True, &quot;global_symbol&quot;: &quot;main&quot;, &quot;tir.noalias&quot;: True}
   buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1214,7 +1214,7 @@ more cache friendly.</p>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
   &quot;target_host parameter is going to be deprecated. &quot;
-loop permutation: 0.117269
+loop permutation: 0.112057
 @main = primfn(A_1: handle, B_1: handle, C_1: handle) -&gt; ()
   attr = {&quot;from_legacy_te_schedule&quot;: True, &quot;global_symbol&quot;: &quot;main&quot;, &quot;tir.noalias&quot;: True}
   buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1292,7 +1292,7 @@ optimized schedule.</p>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
   &quot;target_host parameter is going to be deprecated. &quot;
-array packing: 0.109018
+array packing: 0.106499
 @main = primfn(A_1: handle, B_1: handle, C_1: handle) -&gt; ()
   attr = {&quot;from_legacy_te_schedule&quot;: True, &quot;global_symbol&quot;: &quot;main&quot;, &quot;tir.noalias&quot;: True}
   buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1368,7 +1368,7 @@ to `C</cite> when all the block results are ready.</p>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
   &quot;target_host parameter is going to be deprecated. &quot;
-block caching: 0.110431
+block caching: 0.102391
 @main = primfn(A_1: handle, B_1: handle, C_1: handle) -&gt; ()
   attr = {&quot;from_legacy_te_schedule&quot;: True, &quot;global_symbol&quot;: &quot;main&quot;, &quot;tir.noalias&quot;: True}
   buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1437,7 +1437,7 @@ of thread-level parallelization.</p>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
   &quot;target_host parameter is going to be deprecated. &quot;
-parallelization: 0.144564
+parallelization: 0.134030
 @main = primfn(A_1: handle, B_1: handle, C_1: handle) -&gt; ()
   attr = {&quot;from_legacy_te_schedule&quot;: True, &quot;global_symbol&quot;: &quot;main&quot;, &quot;tir.noalias&quot;: True}
   buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1499,13 +1499,13 @@ working, we can compare the results.</p>
 </pre></div>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>        Operator                  Timing             Performance
-            none            3.4495668072                     1.0
-        blocking     0.28671782990000005     0.08311705379978647
-   vectorization     0.33077472939999997      0.0958887732539636
-loop permutation            0.1172686762     0.03399518918005433
-   array packing     0.10901774150000001     0.03160331357330322
-   block caching            0.1104314359    0.032013131524081646
- parallelization            0.1445644901     0.04190801285490755
+            none            3.2913449831                     1.0
+        blocking            0.2948428185      0.0895812562991492
+   vectorization            0.3342876312      0.1015656617329571
+loop permutation     0.11205738779999999     0.03404607793330043
+   array packing            0.1064986515    0.032357182868048284
+   block caching            0.1023906918    0.031109073137499513
+ parallelization            0.1340297455    0.040721876979836424
 </pre></div>
 </div>
 <p>Note that the outputs on the web page reflect the running times on a
@@ -1537,7 +1537,6 @@ is</p>
 you can build generic templates of the matrix multiplication and other
 operations with tunable parameters that allows you to automatically optimize
 the computation for specific platforms.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  1.065 seconds)</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-tensor-expr-get-started-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../_downloads/40a01cffb015a67aaec0fad7e27cf80d/tensor_expr_get_started.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">tensor_expr_get_started.py</span></code></a></p>