[tvm-site] branch asf-site updated: deploying docs (apache/tvm@bb00a15c265ba12341aede06bbbf216dda585211)

[tq...@apache.org]

This is an automated email from the ASF dual-hosted git repository.

tqchen pushed a commit to branch asf-site
in repository https://gitbox.apache.org/repos/asf/tvm-site.git


The following commit(s) were added to refs/heads/asf-site by this push:
     new c08107473 deploying docs (apache/tvm@bb00a15c265ba12341aede06bbbf216dda585211)
c08107473 is described below

commit c08107473ad7b390ef5f4f121996549d94bd6b01
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Thu Aug 25 20:47:07 2022 +0000

    deploying docs (apache/tvm@bb00a15c265ba12341aede06bbbf216dda585211)
---
 .../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    |   2 +-
 .../how_to/extend_tvm/sg_execution_times.rst.txt   |  10 +-
 .../how_to/extend_tvm/use_pass_instrument.rst.txt  |  16 +-
 .../optimize_operators/opt_conv_cuda.rst.txt       |   2 +-
 .../optimize_operators/opt_conv_tensorcore.rst.txt |   2 +-
 .../how_to/optimize_operators/opt_gemm.rst.txt     |  16 +-
 .../optimize_operators/sg_execution_times.rst.txt  |   8 +-
 .../sg_execution_times.rst.txt                     |  14 +-
 .../tune_conv2d_layer_cuda.rst.txt                 | 989 ++-------------------
 .../tune_network_cuda.rst.txt                      |   2 +-
 .../tune_network_x86.rst.txt                       |   4 +-
 .../tune_sparse_x86.rst.txt                        |  20 +-
 .../tune_with_autotvm/sg_execution_times.rst.txt   |   4 +-
 .../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  |   8 +-
 .../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 |  16 +-
 .../how_to/work_with_schedules/tensorize.rst.txt   |   2 +-
 .../tutorials/autotvm/sg_execution_times.rst.txt   |   4 +-
 .../frontend/deploy_classification.rst.txt         |   2 +-
 .../tutorials/frontend/deploy_detection.rst.txt    |   2 +-
 .../tutorials/frontend/sg_execution_times.rst.txt  |   6 +-
 .../tutorials/optimize/sg_execution_times.rst.txt  |   6 +-
 .../topic/vta/tutorials/sg_execution_times.rst.txt |   6 +-
 .../tutorial/auto_scheduler_matmul_x86.rst.txt     |   7 +-
 docs/_sources/tutorial/autotvm_matmul_x86.rst.txt  |  20 +-
 docs/_sources/tutorial/autotvm_relay_x86.rst.txt   |  54 +-
 .../tutorial/cross_compilation_and_rpc.rst.txt     |   2 +-
 docs/_sources/tutorial/intro_topi.rst.txt          |   2 +-
 docs/_sources/tutorial/sg_execution_times.rst.txt  |  20 +-
 .../tutorial/tensor_expr_get_started.rst.txt       |  49 +-
 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       |  16 +-
 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 |  22 +-
 .../deploy_models/deploy_model_on_android.html     |   2 +-
 .../deploy_object_detection_pytorch.html           |  18 +-
 docs/how_to/deploy_models/deploy_prequantized.html |   7 +-
 .../deploy_models/deploy_prequantized_tflite.html  |   4 +-
 docs/how_to/deploy_models/deploy_quantized.html    |   2 +-
 docs/how_to/deploy_models/deploy_ssd_gluoncv.html  |  37 +-
 docs/how_to/deploy_models/sg_execution_times.html  |  18 +-
 .../extend_tvm/bring_your_own_datatypes.html       |   2 +-
 docs/how_to/extend_tvm/sg_execution_times.html     |  10 +-
 docs/how_to/extend_tvm/use_pass_instrument.html    |  16 +-
 docs/how_to/optimize_operators/opt_conv_cuda.html  |   2 +-
 .../optimize_operators/opt_conv_tensorcore.html    |   2 +-
 docs/how_to/optimize_operators/opt_gemm.html       |  16 +-
 .../optimize_operators/sg_execution_times.html     |   8 +-
 .../sg_execution_times.html                        |  14 +-
 .../tune_conv2d_layer_cuda.html                    | 989 ++-------------------
 .../tune_with_autoscheduler/tune_network_cuda.html |   2 +-
 .../tune_with_autoscheduler/tune_network_x86.html  |   4 +-
 .../tune_with_autoscheduler/tune_sparse_x86.html   |  20 +-
 .../tune_with_autotvm/sg_execution_times.html      |   4 +-
 .../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     |   8 +-
 .../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    |  16 +-
 docs/how_to/work_with_schedules/tensorize.html     |   2 +-
 docs/install/nnpack.html                           |  12 +-
 docs/reference/api/python/auto_scheduler.html      |   4 +-
 .../api/typedoc/classes/bytestreamreader.html      |  12 +-
 .../api/typedoc/classes/cachedcallstack.html       |  34 +-
 docs/reference/api/typedoc/classes/dldatatype.html |  12 +-
 docs/reference/api/typedoc/classes/dldevice.html   |  10 +-
 .../reference/api/typedoc/classes/environment.html |  12 +-
 docs/reference/api/typedoc/classes/ffilibrary.html |  20 +-
 .../api/typedoc/classes/graphexecutor.html         |  16 +-
 docs/reference/api/typedoc/classes/instance.html   |  40 +-
 docs/reference/api/typedoc/classes/memory.html     |  34 +-
 docs/reference/api/typedoc/classes/module.html     |  10 +-
 docs/reference/api/typedoc/classes/ndarray.html    |  22 +-
 .../api/typedoc/classes/packedfunccell.html        |   6 +-
 docs/reference/api/typedoc/classes/rpcserver.html  |  14 +-
 docs/reference/api/typedoc/classes/scalar.html     |   6 +-
 .../api/typedoc/classes/webgpucontext.html         |  12 +-
 docs/reference/api/typedoc/enums/argtypecode.html  |  30 +-
 .../api/typedoc/enums/aynccallbackcode.html        |   4 +-
 .../api/typedoc/enums/dldatatypecode.html          |   8 +-
 .../api/typedoc/enums/rpcserverstate.html          |  12 +-
 docs/reference/api/typedoc/enums/sizeof.html       |  18 +-
 docs/reference/api/typedoc/index.html              | 112 +--
 .../api/typedoc/interfaces/disposable.html         |   2 +-
 .../api/typedoc/interfaces/functioninfo.html       |   6 +-
 .../api/typedoc/interfaces/libraryprovider.html    |   4 +-
 docs/searchindex.js                                |   2 +-
 .../vta/tutorials/autotvm/sg_execution_times.html  |   4 +-
 .../tutorials/frontend/deploy_classification.html  |   2 +-
 .../vta/tutorials/frontend/deploy_detection.html   |   2 +-
 .../vta/tutorials/frontend/sg_execution_times.html |   6 +-
 .../vta/tutorials/optimize/sg_execution_times.html |   6 +-
 docs/topic/vta/tutorials/sg_execution_times.html   |   6 +-
 docs/tutorial/auto_scheduler_matmul_x86.html       |   3 +-
 docs/tutorial/autotvm_matmul_x86.html              |  20 +-
 docs/tutorial/autotvm_relay_x86.html               | 258 +++---
 docs/tutorial/cross_compilation_and_rpc.html       |   2 +-
 docs/tutorial/intro_topi.html                      |   2 +-
 docs/tutorial/sg_execution_times.html              |  24 +-
 docs/tutorial/tensor_expr_get_started.html         |  45 +-
 122 files changed, 951 insertions(+), 2661 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 bf80cf6c7..294f1dbb7 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  8.367 seconds)
+   **Total running time of the script:** ( 1 minutes  10.152 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 3620959b8..9a89aecf4 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.zipc60e9b81-d247-4e47-9712-9da971d27eeb from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+    Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip2e1302a3-6b30-47de-9cd9-5e36ad7d5de1 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 5d1d91e89..f548f1981 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]
     19%|#9        | 7.99M/41.5M [00:00<00:00, 40.3MB/s]
     35%|###4      | 14.3M/41.5M [00:00<00:01, 27.4MB/s]
     41%|####1     | 17.1M/41.5M [00:00<00:00, 27.0MB/s]
     54%|#####3    | 22.3M/41.5M [00:00<00:00, 32.4MB/s]
     63%|######3   | 26.3M/41.5M [00:00<00:00, 34.9MB/s]
     77%|#######7  | 32.0M/41.5M [00:00<00:00, 39.8MB/s]
     92%|#########2| 38.3M/41.5M [00:01<00:00, 40.8MB/s]
    100%|##########| 41.5M/41.5M [00:01<00:00, 36.3MB/s]
+
      0%|          | 0.00/41.5M [00:00<?, ?B/s]
     15%|#5        | 6.33M/41.5M [00:00<00:01, 35.2MB/s]
     23%|##3       | 9.69M/41.5M [00:00<00:01, 25.7MB/s]
     35%|###4      | 14.3M/41.5M [00:00<00:00, 32.4MB/s]
     43%|####2     | 17.7M/41.5M [00:00<00:00, 26.8MB/s]
     58%|#####7    | 24.0M/41.5M [00:00<00:00, 30.5MB/s]
     82%|########2 | 34.1M/41.5M [00:00<00:00, 46.8MB/s]
     97%|#########7| 40.4M/41.5M [00:01<00:00, 51.6MB/s]
    100%|##########| 41.5M/41.5M [00:01<00:00, 41.1MB/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 cc7a6263e..744d92daa 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]
     45%|####4     | 19.9M/44.7M [00:00<00:00, 208MB/s]
     89%|########9 | 39.8M/44.7M [00:00<00:00, 196MB/s]
    100%|##########| 44.7M/44.7M [00:00<00:00, 191MB/s]
+
      0%|          | 0.00/44.7M [00:00<?, ?B/s]
     39%|###9      | 17.5M/44.7M [00:00<00:00, 184MB/s]
     98%|#########7| 43.7M/44.7M [00:00<00:00, 237MB/s]
    100%|##########| 44.7M/44.7M [00:00<00:00, 230MB/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 0273b9849..7f6e08a21 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  2.116 seconds)
+   **Total running time of the script:** ( 1 minutes  3.303 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 a83ebc9b3..ee3f1a993 100644
--- a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
 
 Computation times
 =================
-**05:09.887** total execution time for **how_to_compile_models** files:
+**05:14.806** total execution time for **how_to_compile_models** files:
 
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)       | 01:08.367 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)       | 01:10.152 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:02.116 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:03.303 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)         | 00:39.739 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)         | 00:40.153 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)       | 00:28.295 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)       | 00:28.392 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)           | 00:25.662 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)           | 00:25.581 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)         | 00:25.409 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)         | 00:24.680 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)         | 00:22.219 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)         | 00:23.267 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)       | 00:19.599 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)       | 00:20.311 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)           | 00:15.675 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)           | 00:16.521 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)             | 00:02.805 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)             | 00:02.444 | 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 d054e7a9a..f914db32f 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)  
-      15.9978      15.9742      16.2668      15.8427       0.1235   
+      16.6787      16.4114      17.3335      16.1247       0.5068   
                
 
 
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 c676c3a7b..9fc311bd5 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]
      9%|9         | 15.3M/170M [00:00<00:01, 160MB/s]
     23%|##2       | 38.7M/170M [00:00<00:00, 210MB/s]
     36%|###5      | 61.0M/170M [00:00<00:00, 219MB/s]
     49%|####8     | 82.9M/170M [00:00<00:00, 224MB/s]
     65%|######4   | 110M/170M [00:00<00:00, 245MB/s] 
     80%|#######9  | 135M/170M [00:00<00:00, 251MB/s]
     96%|#########6| 163M/170M [00:00<00:00, 266MB/s]
    100%|##########| 170M/170M [00:00<00:00, 245MB/s]
+
      0%|          | 0.00/170M [00:00<?, ?B/s]
     10%|9         | 16.4M/170M [00:00<00:00, 172MB/s]
     23%|##2       | 38.9M/170M [00:00<00:00, 209MB/s]
     38%|###7      | 63.9M/170M [00:00<00:00, 234MB/s]
     52%|#####2    | 88.6M/170M [00:00<00:00, 244MB/s]
     67%|######6   | 113M/170M [00:00<00:00, 249MB/s] 
     81%|########1 | 138M/170M [00:00<00:00, 251MB/s]
     95%|#########5| 162M/170M [00:00<00:00, 236MB/s]
    100%|##########| 170M/170M [00:00<00:00, 237MB/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:** ( 3 minutes  1.285 seconds)
+   **Total running time of the script:** ( 3 minutes  3.307 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 e48ba22df..00b4a05c6 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]
     76%|#######6  | 10.3M/13.6M [00:00<00:00, 108MB/s]
    100%|##########| 13.6M/13.6M [00:00<00:00, 114MB/s]
+
      0%|          | 0.00/13.6M [00:00<?, ?B/s]
    100%|##########| 13.6M/13.6M [00:00<00:00, 164MB/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)  
-      90.3389      90.2780      95.2355      90.0115       0.5432   
+      90.3940      90.2899      95.7821      90.0619       0.5797   
                
 
 
@@ -461,7 +461,7 @@ TODO
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  10.505 seconds)
+   **Total running time of the script:** ( 1 minutes  10.791 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 b31d35d5a..6ef64ec45 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)  
-      121.2638     121.1995     122.8537     120.5858      0.3461   
+      121.9901     121.9944     122.6127     121.3698      0.2601   
                
 
 
@@ -476,7 +476,7 @@ Here we give an example of how to measure performance of TVM compiled models.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 2 minutes  0.142 seconds)
+   **Total running time of the script:** ( 2 minutes  0.221 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 0552e6088..06e7f949c 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  43.057 seconds)
+   **Total running time of the script:** ( 1 minutes  35.068 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 3c350b180..9cf6a5456 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]
      5%|4         | 6405/132723 [00:00<00:01, 64045.33KB/s]
     11%|#         | 14532/132723 [00:00<00:01, 74174.00KB/s]
     17%|#7        | 22786/132723 [00:00<00:01, 77989.05KB/s]
     23%|##3       | 31062/132723 [00:00<00:01, 79870.53KB/s]
     29%|##9       | 39050/132723 [00:00<00:01, 63817.47KB/s]
     36%|###5      | 47259/132723 [00:00<00:01, 69142.96KB/s]
     41%|####1     | 54541/132723 [00:00<00:01, 65836.39KB/s]
     47%|####7     | 62694/132723 [00:00<00:00, 70269.61KB/s]
     53%|#####3    | 70953/132723 [00:00<00:00, 73811.13KB/s]
     60%|#####9    | 79237/132723 [00:01<00:00, 76437.62KB/s]
     66%|######5   | 87029/132723 [00:01<00:00, 63661.69KB/s]
     72%|#######1  | 95203/132723 [00:01<00:00, 68322.92KB/s]
     77%|#######7  | 102424/132723 [00:01<00:00, 47108.49KB/s]
     83%|########2 | 109911/132723 [00:01<00:00, 52856.76KB/s]
     88%|########7 | 116240/132723 [00:01<00:00, 50030.85KB/s]
     93%|########
 #3| 123697/132723 [00:01<00:00, 55624.53KB/s]
     99%|#########8| 131117/132723 [00:02<00:00, 60186.94KB/s]
    100%|##########| 132723/132723 [00:02<00:00, 63026.76KB/s]
+
      0%|          | 0/132723 [00:00<?, ?KB/s]
      5%|5         | 6779/132723 [00:00<00:01, 67785.38KB/s]
     11%|#1        | 14829/132723 [00:00<00:01, 75259.86KB/s]
     17%|#7        | 22863/132723 [00:00<00:01, 77577.29KB/s]
     23%|##3       | 31028/132723 [00:00<00:01, 79181.53KB/s]
     29%|##9       | 38947/132723 [00:00<00:01, 55828.76KB/s]
     35%|###5      | 47017/132723 [00:00<00:01, 62452.77KB/s]
     41%|####1     | 54794/132723 [00:00<00:01, 66673.58KB/s]
     47%|####7     | 62861/132723 [00:00<00:00, 70625.36KB/s]
     53%|#####3    | 71000/132723 [00:01<00:00, 73718.42KB/s]
     60%|#####9    | 79170/132723 [00:01<00:00, 76040.28KB/s]
     66%|######5   | 87012/132723 [00:01<00:00, 61985.91KB/s]
     72%|#######1  | 95085/132723 [00:01<00:00, 66730.06KB/s]
     77%|#######7  | 102250/132723 [00:01<00:00, 56886.75KB/s]
     83%|########3 | 110335/132723 [00:01<00:00, 62656.00KB/s]
     89%|########9 | 118414/132723 [00:01<00:00, 67296.60KB/s]
     95%|########
 #5| 126414/132723 [00:01<00:00, 70696.38KB/s]
    100%|##########| 132723/132723 [00:01<00:00, 68049.58KB/s]
 
 
 
@@ -241,7 +241,7 @@ Display result
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 2 minutes  35.223 seconds)
+   **Total running time of the script:** ( 2 minutes  43.432 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 d63bced31..322fae939 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
 =================
-**11:45.414** total execution time for **how_to_deploy_models** files:
+**11:49.860** total execution time for **how_to_deploy_models** files:
 
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:01.285 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:03.307 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)                           | 02:35.223 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)                           | 02:43.432 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)           | 02:00.142 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)           | 02:00.221 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)                               | 01:43.057 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)                               | 01:35.068 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)                         | 01:10.505 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)                         | 01:10.791 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)                 | 00:29.822 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)                 | 00:30.587 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``)                       | 00:22.872 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``)                       | 00:23.488 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)                       | 00:22.500 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)                       | 00:22.959 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``)                                     | 00:00.007 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
index ca394856a..05eb99775 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.zip0f41d8d6-03f1-40d0-89d9-2a446b83a0b3 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+    Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip1d4bd40c-67ea-4037-8527-382c77200cde from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
 
 
 
diff --git a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
index a8b42ddf4..7a44195e9 100644
--- a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
 
 Computation times
 =================
-**00:40.844** total execution time for **how_to_extend_tvm** files:
+**00:42.229** 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``) | 00:37.653 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:38.986 | 0.0 MB |
 +-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)           | 00:02.201 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)           | 00:02.265 | 0.0 MB |
 +-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)                     | 00:00.983 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)                     | 00:00.969 | 0.0 MB |
 +-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``)       | 00:00.007 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``)       | 00:00.008 | 0.0 MB |
 +-------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
index 98715155f..658644e81 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: 7142us [7142us] (46.78%; 46.78%)
-    FoldScaleAxis: 8127us [7us] (53.22%; 53.22%)
-            FoldConstant: 8120us [1722us] (53.18%; 99.92%)
-                    InferType: 6398us [6398us] (41.90%; 78.79%)
+    InferType: 6815us [6815us] (46.32%; 46.32%)
+    FoldScaleAxis: 7898us [6us] (53.68%; 53.68%)
+            FoldConstant: 7892us [1632us] (53.64%; 99.93%)
+                    InferType: 6260us [6260us] (42.55%; 79.32%)
 
 
 
@@ -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: 6599us [6599us] (45.03%; 45.03%)
-    FoldScaleAxis: 8054us [6us] (54.97%; 54.97%)
-            FoldConstant: 8049us [1684us] (54.93%; 99.93%)
-                    InferType: 6365us [6365us] (43.43%; 79.08%)
+    InferType: 6304us [6304us] (44.65%; 44.65%)
+    FoldScaleAxis: 7816us [5us] (55.35%; 55.35%)
+            FoldConstant: 7811us [1615us] (55.32%; 99.94%)
+                    InferType: 6196us [6196us] (43.88%; 79.33%)
 
 
 
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 f721564fb..af0a42633 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: 54.143767 ms
+    Convolution: 54.200517 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 dadaa2ec7..001713e60 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: 6.650397 ms
+    conv2d with tensor core: 6.578599 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 5ea0097a0..ad4bfe191 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: 0.018469
-    Baseline: 3.422294
+    Numpy running time: 0.019346
+    Baseline: 3.307523
 
 
 
@@ -239,7 +239,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
 
  .. code-block:: none
 
-    Opt1: 0.297363
+    Opt1: 0.316917
 
 
 
@@ -342,7 +342,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
 
  .. code-block:: none
 
-    Opt2: 0.332500
+    Opt2: 0.343967
 
 
 
@@ -438,7 +438,7 @@ the access pattern for A matrix is more cache friendly.
 
  .. code-block:: none
 
-    Opt3: 0.115016
+    Opt3: 0.120405
 
 
 
@@ -563,7 +563,7 @@ flattening.
 
  .. code-block:: none
 
-    Opt4: 0.110444
+    Opt4: 0.109842
 
 
 
@@ -685,7 +685,7 @@ write to C when all the block results are ready.
 
  .. code-block:: none
 
-    Opt5: 0.111119
+    Opt5: 0.111244
 
 
 
@@ -810,7 +810,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
 
  .. code-block:: none
 
-    Opt6: 0.146974
+    Opt6: 0.147428
 
 
 
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 580aa50bf..4ddb91859 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
 =================
-**00:34.416** total execution time for **how_to_optimize_operators** files:
+**00:34.619** total execution time for **how_to_optimize_operators** files:
 
 +-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)                       | 00:32.222 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)                       | 00:32.437 | 0.0 MB |
 +-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.202 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.204 | 0.0 MB |
 +-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)             | 00:00.992 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)             | 00:00.978 | 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 38b031e1e..bdca07046 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
 =================
-**06:15.371** total execution time for **how_to_tune_with_autoscheduler** files:
+**06:09.622** 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``) | 03:17.525 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 03:19.356 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)             | 01:22.050 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)             | 01:24.177 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)           | 00:46.881 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)           | 00:47.595 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)               | 00:31.268 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)               | 00:20.481 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)           | 00:08.992 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)           | 00:09.077 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)             | 00:08.654 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)             | 00:08.936 | 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 1d42f56e0..83cf75773 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
@@ -240,483 +240,38 @@ 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, [4]), storage_scope = local;
-      allocate(pad_temp.shared: Pointer(shared float32), float32, [1568]), storage_scope = shared;
-      allocate(kernel.shared: Pointer(shared float32), float32, [512]), storage_scope = shared;
-      attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
-        conv2d_nchw_1: Buffer(conv2d_nchw, float32, [1], [], scope="local", align=4)[0] = 0f32
-        conv2d_nchw_1[1] = 0f32
-        conv2d_nchw_1[2] = 0f32
-        conv2d_nchw_1[3] = 0f32
+      attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 64;
+      allocate(conv2d_nchw: Pointer(local float32), float32, [7]), storage_scope = local;
+      allocate(pad_temp.shared: Pointer(shared float32), float32, [2016]), storage_scope = shared;
+      allocate(kernel.shared: Pointer(shared float32), float32, [768]), storage_scope = shared;
+      attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+        for (yy.inner.init: int32, 0, 7) {
+          conv2d_nchw_1: Buffer(conv2d_nchw, float32, [7], [], scope="local", align=16)[yy.inner.init] = 0f32
+        }
         for (rc.outer.outer: int32, 0, 16) {
-          for (ry.outer.outer: int32, 0, 3) {
-            let cse_var_2: int32 = (rc.outer.outer*288)
-            let cse_var_1: int32 = (ry.outer.outer*3)
-             {
-              attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
-              pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1568], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) - 8)], 0f32, dtype=float32)
-              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
-              pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else((((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) + 188)], 0f32, dtype=float32)
-              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
-              pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else((((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) + 384)], 0f32, dtype=float32)
-              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
-              pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else((((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) + 580)], 0f32, dtype=float32)
-              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
-              pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else((((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) + 776)], 0f32, dtype=float32)
-              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
-              pad_temp.shared_1[(threadIdx.x_1 + 980)] = @tir.if_then_else((((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) + 972)], 0f32, dtype=float32)
-              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
-              pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else((((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) + 1168)], 0f32, dtype=float32)
-              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
-              pad_temp.shared_1[(threadIdx.x_1 + 1372)] = @tir.if_then_else((((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) + 1364)], 0f32, dtype=float32)
-              attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
-              kernel.shared_1: Buffer(kernel.shared, float32, [512], [], scope="shared")[threadIdx.x_2] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 32)*4608)) + cse_var_2) + (floormod(threadIdx.x_2, 32)*9)) + cse_var_1)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
-              kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 196), 32)*4608)) + cse_var_2) + (floormod((threadIdx.x_2 + 4), 32)*9)) + cse_var_1)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
-              if @tir.likely((threadIdx.x_2 < 120), dtype=bool) {
-                kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 392), 32)*4608)) + cse_var_2) + (floormod((threadIdx.x_2 + 8), 32)*9)) + cse_var_1)]
-              }
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[(floordiv(threadIdx.x, 49)*32)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 128)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 256)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 384)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 1)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 129)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 257)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 385)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 2)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 130)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 258)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 386)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 3)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 131)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 259)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 387)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 4)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 132)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 260)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 388)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 5)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 133)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 261)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 389)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 6)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 134)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 262)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 390)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 7)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 135)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 263)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 391)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 8)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 136)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 264)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 392)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 9)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 137)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 265)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 393)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 10)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 138)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 266)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 394)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 11)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 139)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 267)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 395)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 12)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 140)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 268)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 396)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 13)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 141)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 269)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 397)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 14)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 142)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 270)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 398)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 15)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 143)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 271)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 399)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 784)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 16)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 784)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 144)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 784)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 272)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 784)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 400)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 833)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 17)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 833)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 145)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 833)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 273)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 833)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 401)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 882)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 18)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 882)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 146)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 882)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 274)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 882)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 402)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 931)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 19)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 931)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 147)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 931)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 275)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 931)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 403)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 980)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 20)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 980)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 148)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 980)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 276)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 980)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 404)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1029)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 21)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1029)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 149)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1029)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 277)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1029)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 405)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1078)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 22)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1078)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 150)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1078)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 278)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1078)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 406)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1127)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 23)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1127)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 151)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1127)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 279)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1127)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 407)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1176)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 24)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1176)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 152)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1176)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 280)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1176)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 408)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1225)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 25)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1225)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 153)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1225)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 281)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1225)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 409)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1274)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 26)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1274)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 154)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1274)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 282)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1274)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 410)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1323)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 27)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1323)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 155)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1323)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 283)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1323)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 411)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1372)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 28)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1372)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 156)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1372)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 284)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1372)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 412)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1421)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 29)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1421)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 157)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1421)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 285)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1421)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 413)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1470)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 30)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1470)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 158)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1470)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 286)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1470)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 414)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1519)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 31)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1519)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 159)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1519)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 287)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1519)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 415)]))
-              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
-              pad_temp.shared_1[threadIdx.x_1] = @tir.if_then_else(((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) - 7)], 0f32, dtype=float32)
-              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
-              pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) + 189)], 0f32, dtype=float32)
-              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
-              pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) + 385)], 0f32, dtype=float32)
-              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
-              pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else(((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) + 581)], 0f32, dtype=float32)
-              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
-              pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) + 777)], 0f32, dtype=float32)
-              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
-              pad_temp.shared_1[(threadIdx.x_1 + 980)] = @tir.if_then_else(((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) + 973)], 0f32, dtype=float32)
-              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
-              pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) + 1169)], 0f32, dtype=float32)
-              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
-              pad_temp.shared_1[(threadIdx.x_1 + 1372)] = @tir.if_then_else(((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) + 1365)], 0f32, dtype=float32)
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
-              kernel.shared_1[threadIdx.x_2] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 32)*4608)) + cse_var_2) + (floormod(threadIdx.x_2, 32)*9)) + cse_var_1) + 1)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
-              kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 196), 32)*4608)) + cse_var_2) + (floormod((threadIdx.x_2 + 4), 32)*9)) + cse_var_1) + 1)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
-              if @tir.likely((threadIdx.x_2 < 120), dtype=bool) {
-                kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 392), 32)*4608)) + cse_var_2) + (floormod((threadIdx.x_2 + 8), 32)*9)) + cse_var_1) + 1)]
+          for (rx.outer.outer: int32, 0, 3) {
+            for (ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer: int32, 0, 36) {
+              attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+              pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2016], [], scope="shared")[((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_1)] = @tir.if_then_else(((((1 <= floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*8) + floordiv(threadIdx.x_1, 7)), 9)) && (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*8) + floordiv(threadIdx.x_1, 7)), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_ [...]
+            }
+            for (ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer_1: int32, 0, 14) {
+              attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+              if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer_1*7) + floordiv(threadIdx.x_2, 8)) < 96), dtype=bool) {
+                kernel.shared_1: Buffer(kernel.shared, float32, [768], [], scope="shared")[((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer_1*56) + threadIdx.x_2)] = kernel[((((((blockIdx.x*36864) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer_1*7) + floordiv(threadIdx.x_2, 8)), 12)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer_1*56) + threadIdx.x_2), 96), 3)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer_ [...]
               }
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[(floordiv(threadIdx.x, 49)*32)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 128)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 256)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 384)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 1)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 129)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 257)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 385)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 2)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 130)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 258)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 386)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 3)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 131)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 259)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 387)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 4)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 132)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 260)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 388)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 5)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 133)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 261)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 389)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 6)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 134)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 262)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 390)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 7)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 135)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 263)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 391)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 8)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 136)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 264)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 392)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 9)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 137)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 265)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 393)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 10)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 138)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 266)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 394)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 11)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 139)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 267)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 395)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 12)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 140)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 268)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 396)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 13)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 141)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 269)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 397)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 14)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 142)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 270)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 398)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 15)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 143)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 271)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 399)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 784)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 16)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 784)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 144)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 784)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 272)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 784)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 400)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 833)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 17)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 833)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 145)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 833)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 273)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 833)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 401)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 882)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 18)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 882)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 146)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 882)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 274)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 882)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 402)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 931)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 19)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 931)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 147)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 931)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 275)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 931)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 403)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 980)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 20)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 980)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 148)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 980)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 276)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 980)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 404)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1029)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 21)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1029)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 149)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1029)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 277)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1029)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 405)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1078)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 22)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1078)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 150)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1078)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 278)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1078)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 406)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1127)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 23)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1127)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 151)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1127)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 279)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1127)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 407)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1176)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 24)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1176)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 152)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1176)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 280)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1176)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 408)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1225)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 25)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1225)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 153)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1225)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 281)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1225)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 409)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1274)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 26)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1274)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 154)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1274)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 282)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1274)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 410)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1323)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 27)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1323)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 155)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1323)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 283)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1323)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 411)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1372)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 28)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1372)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 156)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1372)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 284)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1372)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 412)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1421)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 29)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1421)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 157)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1421)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 285)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1421)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 413)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1470)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 30)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1470)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 158)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1470)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 286)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1470)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 414)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1519)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 31)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1519)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 159)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1519)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 287)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1519)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 415)]))
-              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
-              pad_temp.shared_1[threadIdx.x_1] = @tir.if_then_else((((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) - 6)], 0f32, dtype=float32)
-              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
-              pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else((((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) + 190)], 0f32, dtype=float32)
-              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
-              pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else((((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) + 386)], 0f32, dtype=float32)
-              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
-              pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else((((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) + 582)], 0f32, dtype=float32)
-              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
-              pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else((((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) + 778)], 0f32, dtype=float32)
-              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
-              pad_temp.shared_1[(threadIdx.x_1 + 980)] = @tir.if_then_else((((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) + 974)], 0f32, dtype=float32)
-              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
-              pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else((((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) + 1170)], 0f32, dtype=float32)
-              attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
-              pad_temp.shared_1[(threadIdx.x_1 + 1372)] = @tir.if_then_else((((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) + 1366)], 0f32, dtype=float32)
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
-              kernel.shared_1[threadIdx.x_2] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 32)*4608)) + cse_var_2) + (floormod(threadIdx.x_2, 32)*9)) + cse_var_1) + 2)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
-              kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 196), 32)*4608)) + cse_var_2) + (floormod((threadIdx.x_2 + 4), 32)*9)) + cse_var_1) + 2)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
-              if @tir.likely((threadIdx.x_2 < 120), dtype=bool) {
-                kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 392), 32)*4608)) + cse_var_2) + (floormod((threadIdx.x_2 + 8), 32)*9)) + cse_var_1) + 2)]
+            }
+            for (ry.outer.inner: int32, 0, 3) {
+              for (rc.inner: int32, 0, 32) {
+                for (yy.inner: int32, 0, 7) {
+                  conv2d_nchw_1[yy.inner] = (conv2d_nchw_1[yy.inner] + (pad_temp.shared_1[((((rc.inner*63) + (yy.inner*7)) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.inner*3)) + ry.outer.inner)]))
+                }
               }
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[(floordiv(threadIdx.x, 49)*32)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 128)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 256)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 384)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 1)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 129)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 257)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 385)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 2)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 130)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 258)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 386)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 3)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 131)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 259)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 387)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 4)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 132)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 260)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 388)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 5)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 133)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 261)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 389)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 6)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 134)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 262)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 390)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 7)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 135)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 263)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 391)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 8)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 136)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 264)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 392)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 9)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 137)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 265)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 393)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 10)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 138)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 266)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 394)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 11)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 139)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 267)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 395)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 12)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 140)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 268)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 396)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 13)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 141)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 269)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 397)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 14)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 142)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 270)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 398)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 15)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 143)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 271)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 399)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 784)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 16)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 784)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 144)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 784)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 272)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 784)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 400)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 833)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 17)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 833)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 145)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 833)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 273)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 833)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 401)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 882)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 18)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 882)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 146)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 882)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 274)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 882)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 402)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 931)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 19)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 931)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 147)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 931)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 275)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 931)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 403)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 980)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 20)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 980)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 148)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 980)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 276)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 980)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 404)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1029)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 21)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1029)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 149)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1029)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 277)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1029)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 405)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1078)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 22)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1078)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 150)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1078)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 278)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1078)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 406)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1127)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 23)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1127)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 151)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1127)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 279)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1127)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 407)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1176)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 24)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1176)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 152)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1176)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 280)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1176)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 408)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1225)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 25)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1225)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 153)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1225)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 281)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1225)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 409)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1274)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 26)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1274)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 154)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1274)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 282)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1274)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 410)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1323)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 27)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1323)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 155)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1323)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 283)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1323)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 411)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1372)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 28)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1372)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 156)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1372)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 284)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1372)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 412)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1421)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 29)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1421)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 157)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1421)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 285)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1421)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 413)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1470)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 30)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1470)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 158)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1470)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 286)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1470)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 414)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1519)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 31)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1519)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 159)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1519)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 287)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1519)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 415)]))
             }
           }
         }
-        compute[((blockIdx.x*784) + threadIdx.x)] = max((conv2d_nchw_1[0] + bias[((blockIdx.x*16) + floordiv(threadIdx.x, 49))]), 0f32)
-        compute[(((blockIdx.x*784) + threadIdx.x) + 196)] = max((conv2d_nchw_1[1] + bias[(((blockIdx.x*16) + floordiv(threadIdx.x, 49)) + 4)]), 0f32)
-        compute[(((blockIdx.x*784) + threadIdx.x) + 392)] = max((conv2d_nchw_1[2] + bias[(((blockIdx.x*16) + floordiv(threadIdx.x, 49)) + 8)]), 0f32)
-        compute[(((blockIdx.x*784) + threadIdx.x) + 588)] = max((conv2d_nchw_1[3] + bias[(((blockIdx.x*16) + floordiv(threadIdx.x, 49)) + 12)]), 0f32)
+        for (i2.inner: int32, 0, 7) {
+          compute[((((blockIdx.x*392) + (floordiv(threadIdx.x, 7)*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[i2.inner] + bias[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
+        }
       }
     }
 
@@ -770,7 +325,7 @@ We build the binary and check its correctness and performance.
 
  .. code-block:: none
 
-    Execution time of this operator: 0.234 ms
+    Execution time of this operator: 0.379 ms
 
 
 
@@ -820,20 +375,20 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
     conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
     conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
     conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=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=4)
-    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=4)
-    conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, 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=7)
     conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
-    conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=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=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=16)
+    conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=32)
+    conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
     conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
-    conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
+    conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
     conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
     conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
     s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
@@ -841,10 +396,10 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
     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=1)
-    compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=4)
-    compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=4)
-    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_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=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=7)
@@ -867,14 +422,14 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
     kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
     kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
     s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-    kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=196)
+    kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
     s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
     pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
     pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
     s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-    pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=196)
+    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", 0)
     s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
 
     CUDA source code:
@@ -892,451 +447,37 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
       #define int64_t long long
       #define uint64_t unsigned long long
     #endif
-    extern "C" __global__ void __launch_bounds__(196) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
-      float conv2d_nchw[4];
-      __shared__ float pad_temp_shared[1568];
-      __shared__ float kernel_shared[512];
-      conv2d_nchw[0] = 0.000000e+00f;
-      conv2d_nchw[1] = 0.000000e+00f;
-      conv2d_nchw[2] = 0.000000e+00f;
-      conv2d_nchw[3] = 0.000000e+00f;
+    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[7];
+      __shared__ float pad_temp_shared[2016];
+      __shared__ float kernel_shared[768];
+      for (int yy_inner_init = 0; yy_inner_init < 7; ++yy_inner_init) {
+        conv2d_nchw[yy_inner_init] = 0.000000e+00f;
+      }
       for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
-        for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
+        for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
           __syncthreads();
-          pad_temp_shared[((int)threadIdx.x)] = ((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) - 8)] : 0.000000e+00f);
-          pad_temp_shared[(((int)threadIdx.x) + 196)] = ((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 188)] : 0.000000e+00f);
-          pad_temp_shared[(((int)threadIdx.x) + 392)] = ((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 384)] : 0.000000e+00f);
-          pad_temp_shared[(((int)threadIdx.x) + 588)] = ((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 580)] : 0.000000e+00f);
-          pad_temp_shared[(((int)threadIdx.x) + 784)] = ((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 776)] : 0.000000e+00f);
-          pad_temp_shared[(((int)threadIdx.x) + 980)] = ((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 972)] : 0.000000e+00f);
-          pad_temp_shared[(((int)threadIdx.x) + 1176)] = ((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 1168)] : 0.000000e+00f);
-          pad_temp_shared[(((int)threadIdx.x) + 1372)] = ((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 1364)] : 0.000000e+00f);
-          kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 5) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) & 31) * 9)) + (ry_outer_outer * 3))];
-          kernel_shared[(((int)threadIdx.x) + 196)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 196) >> 5) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 4) & 31) * 9)) + (ry_outer_outer * 3))];
-          if (((int)threadIdx.x) < 120) {
-            kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) >> 5) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) & 31) * 9)) + (ry_outer_outer * 3))];
+          for (int ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer = 0; ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer < 36; ++ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer) {
+            pad_temp_shared[((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x))] = (((((1 <= (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 8) + (((int)threadIdx.x) / 7)) % 9)) && ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 8) + (((int)threadIdx.x) / 7)) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer [...]
           }
-          __syncthreads();
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[((((int)threadIdx.x) / 49) * 32)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 128)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 256)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 384)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 1)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 129)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 257)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 385)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 2)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 130)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 258)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 386)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 3)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 131)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 259)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 387)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 4)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 132)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 260)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 388)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 5)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 133)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 261)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 389)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 6)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 134)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 262)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 390)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 7)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 135)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 263)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 391)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 8)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 136)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 264)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 392)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 9)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 137)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 265)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 393)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 10)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 138)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 266)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 394)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 11)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 139)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 267)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 395)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 12)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 140)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 268)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 396)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 13)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 141)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 269)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 397)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 14)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 142)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 270)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 398)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 15)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 143)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 271)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 399)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 784)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 16)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 784)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 144)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 784)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 272)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 784)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 400)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 833)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 17)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 833)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 145)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 833)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 273)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 833)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 401)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 882)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 18)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 882)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 146)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 882)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 274)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 882)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 402)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 931)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 19)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 931)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 147)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 931)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 275)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 931)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 403)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 980)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 20)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 980)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 148)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 980)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 276)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 980)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 404)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1029)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 21)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1029)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 149)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1029)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 277)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1029)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 405)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1078)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 22)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1078)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 150)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1078)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 278)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1078)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 406)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 23)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 151)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 279)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 407)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1176)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 24)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1176)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 152)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1176)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 280)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1176)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 408)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1225)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 25)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1225)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 153)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1225)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 281)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1225)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 409)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1274)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 26)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1274)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 154)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1274)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 282)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1274)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 410)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 27)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 155)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 283)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 411)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1372)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 28)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1372)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 156)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1372)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 284)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1372)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 412)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1421)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 29)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1421)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 157)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1421)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 285)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1421)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 413)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1470)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 30)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1470)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 158)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1470)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 286)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1470)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 414)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1519)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 31)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1519)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 159)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1519)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 287)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1519)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 415)]));
-          __syncthreads();
-          pad_temp_shared[((int)threadIdx.x)] = (((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) - 7)] : 0.000000e+00f);
-          pad_temp_shared[(((int)threadIdx.x) + 196)] = (((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 189)] : 0.000000e+00f);
-          pad_temp_shared[(((int)threadIdx.x) + 392)] = (((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 385)] : 0.000000e+00f);
-          pad_temp_shared[(((int)threadIdx.x) + 588)] = (((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 581)] : 0.000000e+00f);
-          pad_temp_shared[(((int)threadIdx.x) + 784)] = (((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 777)] : 0.000000e+00f);
-          pad_temp_shared[(((int)threadIdx.x) + 980)] = (((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 973)] : 0.000000e+00f);
-          pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 1169)] : 0.000000e+00f);
-          pad_temp_shared[(((int)threadIdx.x) + 1372)] = (((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 1365)] : 0.000000e+00f);
-          kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 5) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) & 31) * 9)) + (ry_outer_outer * 3)) + 1)];
-          kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 196) >> 5) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 4) & 31) * 9)) + (ry_outer_outer * 3)) + 1)];
-          if (((int)threadIdx.x) < 120) {
-            kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) >> 5) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) & 31) * 9)) + (ry_outer_outer * 3)) + 1)];
+          for (int ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 = 0; ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 < 14; ++ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1) {
+            if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 * 7) + (((int)threadIdx.x) >> 3)) < 96) {
+              kernel_shared[((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 * 56) + ((int)threadIdx.x))] = kernel[((((((((int)blockIdx.x) * 36864) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 * 7) + (((int)threadIdx.x) >> 3)) / 12) * 4608)) + (rc_outer_outer * 288)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 * 56) + ((int)threadIdx.x)) % 96) / 3) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 * 2) + ((int)threadIdx.x)) % 3) * 3)) + rx_outer_outer)];
+            }
           }
           __syncthreads();
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[((((int)threadIdx.x) / 49) * 32)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 128)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 256)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 384)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 1)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 129)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 257)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 385)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 2)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 130)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 258)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 386)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 3)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 131)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 259)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 387)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 4)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 132)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 260)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 388)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 5)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 133)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 261)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 389)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 6)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 134)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 262)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 390)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 7)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 135)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 263)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 391)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 8)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 136)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 264)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 392)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 9)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 137)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 265)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 393)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 10)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 138)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 266)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 394)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 11)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 139)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 267)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 395)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 12)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 140)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 268)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 396)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 13)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 141)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 269)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 397)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 14)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 142)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 270)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 398)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 15)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 143)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 271)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 399)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 784)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 16)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 784)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 144)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 784)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 272)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 784)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 400)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 833)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 17)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 833)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 145)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 833)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 273)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 833)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 401)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 882)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 18)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 882)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 146)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 882)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 274)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 882)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 402)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 931)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 19)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 931)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 147)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 931)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 275)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 931)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 403)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 980)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 20)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 980)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 148)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 980)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 276)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 980)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 404)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1029)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 21)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1029)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 149)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1029)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 277)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1029)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 405)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1078)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 22)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1078)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 150)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1078)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 278)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1078)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 406)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 23)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 151)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 279)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 407)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1176)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 24)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1176)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 152)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1176)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 280)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1176)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 408)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1225)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 25)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1225)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 153)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1225)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 281)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1225)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 409)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1274)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 26)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1274)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 154)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1274)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 282)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1274)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 410)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 27)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 155)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 283)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 411)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1372)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 28)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1372)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 156)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1372)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 284)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1372)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 412)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1421)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 29)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1421)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 157)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1421)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 285)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1421)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 413)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1470)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 30)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1470)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 158)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1470)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 286)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1470)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 414)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1519)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 31)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1519)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 159)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1519)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 287)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1519)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 415)]));
-          __syncthreads();
-          pad_temp_shared[((int)threadIdx.x)] = ((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) - 6)] : 0.000000e+00f);
-          pad_temp_shared[(((int)threadIdx.x) + 196)] = ((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 190)] : 0.000000e+00f);
-          pad_temp_shared[(((int)threadIdx.x) + 392)] = ((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 386)] : 0.000000e+00f);
-          pad_temp_shared[(((int)threadIdx.x) + 588)] = ((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 582)] : 0.000000e+00f);
-          pad_temp_shared[(((int)threadIdx.x) + 784)] = ((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 778)] : 0.000000e+00f);
-          pad_temp_shared[(((int)threadIdx.x) + 980)] = ((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 974)] : 0.000000e+00f);
-          pad_temp_shared[(((int)threadIdx.x) + 1176)] = ((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 1170)] : 0.000000e+00f);
-          pad_temp_shared[(((int)threadIdx.x) + 1372)] = ((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 1366)] : 0.000000e+00f);
-          kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 5) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) & 31) * 9)) + (ry_outer_outer * 3)) + 2)];
-          kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 196) >> 5) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 4) & 31) * 9)) + (ry_outer_outer * 3)) + 2)];
-          if (((int)threadIdx.x) < 120) {
-            kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) >> 5) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) & 31) * 9)) + (ry_outer_outer * 3)) + 2)];
+          for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
+            for (int rc_inner = 0; rc_inner < 32; ++rc_inner) {
+              for (int yy_inner = 0; yy_inner < 7; ++yy_inner) {
+                conv2d_nchw[yy_inner] = (conv2d_nchw[yy_inner] + (pad_temp_shared[((((rc_inner * 63) + (yy_inner * 7)) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_inner * 3)) + ry_outer_inner)]));
+              }
+            }
           }
-          __syncthreads();
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[((((int)threadIdx.x) / 49) * 32)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 128)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 256)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 384)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 1)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 129)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 257)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 385)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 2)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 130)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 258)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 386)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 3)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 131)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 259)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 387)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 4)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 132)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 260)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 388)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 5)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 133)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 261)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 389)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 6)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 134)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 262)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 390)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 7)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 135)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 263)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 391)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 8)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 136)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 264)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 392)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 9)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 137)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 265)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 393)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 10)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 138)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 266)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 394)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 11)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 139)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 267)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 395)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 12)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 140)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 268)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 396)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 13)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 141)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 269)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 397)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 14)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 142)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 270)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 398)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 15)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 143)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 271)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 399)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 784)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 16)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 784)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 144)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 784)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 272)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 784)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 400)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 833)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 17)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 833)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 145)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 833)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 273)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 833)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 401)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 882)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 18)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 882)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 146)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 882)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 274)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 882)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 402)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 931)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 19)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 931)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 147)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 931)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 275)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 931)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 403)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 980)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 20)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 980)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 148)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 980)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 276)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 980)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 404)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1029)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 21)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1029)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 149)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1029)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 277)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1029)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 405)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1078)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 22)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1078)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 150)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1078)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 278)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1078)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 406)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 23)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 151)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 279)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 407)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1176)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 24)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1176)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 152)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1176)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 280)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1176)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 408)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1225)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 25)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1225)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 153)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1225)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 281)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1225)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 409)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1274)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 26)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1274)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 154)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1274)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 282)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1274)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 410)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 27)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 155)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 283)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 411)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1372)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 28)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1372)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 156)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1372)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 284)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1372)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 412)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1421)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 29)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1421)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 157)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1421)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 285)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1421)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 413)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1470)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 30)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1470)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 158)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1470)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 286)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1470)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 414)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1519)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 31)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1519)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 159)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1519)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 287)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1519)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 415)]));
         }
       }
-      compute[((((int)blockIdx.x) * 784) + ((int)threadIdx.x))] = max((conv2d_nchw[0] + bias[((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 49))]), 0.000000e+00f);
-      compute[(((((int)blockIdx.x) * 784) + ((int)threadIdx.x)) + 196)] = max((conv2d_nchw[1] + bias[(((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 49)) + 4)]), 0.000000e+00f);
-      compute[(((((int)blockIdx.x) * 784) + ((int)threadIdx.x)) + 392)] = max((conv2d_nchw[2] + bias[(((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 49)) + 8)]), 0.000000e+00f);
-      compute[(((((int)blockIdx.x) * 784) + ((int)threadIdx.x)) + 588)] = max((conv2d_nchw[3] + bias[(((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 49)) + 12)]), 0.000000e+00f);
+      for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
+        compute[((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i2_inner] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+      }
     }
 
 
@@ -1397,7 +538,7 @@ 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  17.525 seconds)
+   **Total running time of the script:** ( 3 minutes  19.356 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 9186efbe4..66ff7e878 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)  
-       9.8735       9.8832       9.8939       9.8434       0.0218   
+       9.8300       9.8381       9.8576       9.7945       0.0264   
                
 
 
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 58fa2e98e..8d557aba3 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)  
-      753.2478     753.4996     754.0394     752.2046      0.7699   
+      761.9509     761.8104     762.6521     761.3901      0.5247   
                
 
 
@@ -694,7 +694,7 @@ Other Tips
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  22.050 seconds)
+   **Total running time of the script:** ( 1 minutes  24.177 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 90b9d31b5..2ef19a0d3 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
@@ -397,14 +397,14 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
                  placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
                  compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
       buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
-      preflattened_buffer_map = {placeholder_8: placeholder_15: Buffer(placeholder_13, int32, [33], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), placeholder_5: placeholder_19: Buffer(placeholder_10, float32, [128, 256], [])} {
-      for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
-        allocate(compute_4: Pointer(global float32), float32, [1024]), storage_scope = global {
+      preflattened_buffer_map = {placeholder_6: placeholder_15: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_5: placeholder_19: Buffer(placeholder_10, float32, [128, 256], [])} {
+      for (i0.outer.i1.outer.fused: int32, 0, 32) "parallel" {
+        allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global {
           for (nb_j.inner: int32, 0, 2) {
-            for (i.inner.init: int32, 0, 32) {
+            for (i.inner.init: int32, 0, 64) {
               let cse_var_1: int32 = ((i.inner.init*32) + (nb_j.inner*16))
                {
-                compute_5: Buffer(compute_4, float32, [1024], [])[cse_var_1] = 0f32
+                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
@@ -423,11 +423,11 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
               }
             }
             for (elem_idx: int32, 0, let cse_var_2: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
-              for (i.inner: int32, 0, 32) {
+              for (i.inner: int32, 0, 64) {
                 let cse_var_21: int32 = (elem_idx*16)
                 let cse_var_20: int32 = ((i.inner*32) + (nb_j.inner*16))
                 let cse_var_19: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
-                let cse_var_18: int32 = ((floordiv(i0.outer.i1.outer.fused, 16)*8192) + (i.inner*256))
+                let cse_var_18: int32 = ((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i.inner*256))
                 let cse_var_17: int32 = (cse_var_20 + 9)
                 let cse_var_16: int32 = (cse_var_20 + 8)
                 let cse_var_15: int32 = (cse_var_20 + 7)
@@ -464,8 +464,8 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
               }
             }
           }
-          for (i0.inner: int32, 0, 32) {
-            let cse_var_22: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
+          for (i0.inner: int32, 0, 64) {
+            let cse_var_22: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
             compute[ramp(cse_var_22, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
           }
         }
@@ -522,7 +522,7 @@ We build the binary and check its correctness and performance.
 
  .. code-block:: none
 
-    Execution time of this operator: 1.769 ms
+    Execution time of this operator: 1.861 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 3d42b88e3..648ab168f 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
 
 Computation times
 =================
-**00:46.741** total execution time for **how_to_tune_with_autotvm** files:
+**00:45.570** 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``)           | 00:46.706 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)           | 00:45.534 | 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 |
 +--------------------------------------------------------------------------------------------------+-----------+--------+
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 5b054b4ec..55c376590 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: 177.24/177.24   result: MeasureResult(costs=(0.0013061541555555553,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.027951955795288, timestamp=1661454568.118685)        [('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: 0.00/177.24     result: Traceback (most recent call last):
+    No: 9   GFLOPS: 177.21/177.21   result: MeasureResult(costs=(0.0013063413,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8493096828460693, timestamp=1661454039.3630486)       [('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: 0.00/177.21     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: 261.00/261.00   result: MeasureResult(costs=(0.0008869829502762431,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.464146375656128, timestamp=1661454569.0188472)       [('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: 0.00/261.00     result: Traceback (most recent call last):
+    No: 11  GFLOPS: 261.25/261.25   result: MeasureResult(costs=(0.0008861220773480661,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7522459030151367, timestamp=1661454040.2921894)      [('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: 0.00/261.25     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: 0.00/261.00     result: Traceback (most recent call last):
+    No: 13  GFLOPS: 0.00/261.25     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: 0.00/261.00     result: Traceback (most recent call last):
+    No: 14  GFLOPS: 0.00/261.25     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: 5.27/261.00     result: MeasureResult(costs=(0.04395421475,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8496427536010742, timestamp=1661454573.5394044)      [('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: 3.34/261.00     result: MeasureResult(costs=(0.06922530974999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.52052903175354, timestamp=1661454574.777682)   [('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: 0.00/261.00     result: Traceback (most recent call last):
+    No: 15  GFLOPS: 5.48/261.25     result: MeasureResult(costs=(0.04225220625,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8322460651397705, timestamp=1661454044.88521)        [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
+    No: 16  GFLOPS: 3.36/261.25     result: MeasureResult(costs=(0.06893672225,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.58309531211853, timestamp=1661454046.1246612)        [('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: 0.00/261.25     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: 28.14/261.00    result: MeasureResult(costs=(0.008226495357142857,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2804126739501953, timestamp=1661454585.787514)        [('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: 0.00/261.00     result: Traceback (most recent call last):
+    No: 18  GFLOPS: 26.25/261.25    result: MeasureResult(costs=(0.008818050916666665,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1476569175720215, timestamp=1661454057.0324976)       [('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: 0.00/261.25     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: 0.00/261.00     result: Traceback (most recent call last):
+    No: 20  GFLOPS: 0.00/261.25     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: 0.001272
+    Time cost of this operator: 0.001222
 
 
 
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 0269bc38c..951d84926 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  311.6     98.733   (1, 2, 10, 10, 3)  2       1        [311.6]           
-    tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       3.017     0.956    (1, 6, 10, 10)     1       1        [3.017]           
-    tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.982     0.311    (1, 1, 10, 10, 3)  1       1        [0.982]           
-    Total_time                                    -                                             315.6     -        -                  -       -        -                 
+    tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  310.9     98.728   (1, 2, 10, 10, 3)  2       1        [310.9]           
+    tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       3.027     0.961    (1, 6, 10, 10)     1       1        [3.027]           
+    tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.977     0.31     (1, 1, 10, 10, 3)  1       1        [0.977]           
+    Total_time                                    -                                             314.904   -        -                  -       -        -                 
 
 
 
@@ -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  326.4     98.699   (1, 2, 10, 10, 3)  2       1        [326.4]           
-    tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       3.174     0.96     (1, 6, 10, 10)     1       1        [3.174]           
-    tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         1.129     0.341    (1, 1, 10, 10, 3)  1       1        [1.129]           
-    Total_time                                    -                                             330.702   -        -                  -       -        -                 
+    tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  79.812    96.694   (1, 6, 10, 10, 1)  2       1        [79.812]          
+    tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       1.752     2.123    (1, 6, 10, 10)     1       1        [1.752]           
+    tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.976     1.183    (1, 1, 10, 10, 3)  1       1        [0.976]           
+    Total_time                                    -                                             82.541    -        -                  -       -        -                 
 
 
 
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 25ea01250..b8fa272d9 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/tmptk7s37ws/images/random'
+    '/tmp/tmpox6otj9z/images/random'
 
 
 
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
 
  .. code-block:: none
 
-    /tmp/tmptk7s37ws/images/target contains 8144 images
-    /tmp/tmptk7s37ws/images/random contains 5000 images
+    /tmp/tmpox6otj9z/images/target contains 8144 images
+    /tmp/tmpox6otj9z/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: 0.2190 - accuracy: 0.9256 - val_loss: 0.1405 - val_accuracy: 0.9588
+    328/328 - 56s - loss: 0.2119 - accuracy: 0.9289 - val_loss: 0.1397 - val_accuracy: 0.9539
     Epoch 2/3
-    328/328 - 52s - loss: 0.0992 - accuracy: 0.9636 - val_loss: 0.1139 - val_accuracy: 0.9637
+    328/328 - 52s - loss: 0.0976 - accuracy: 0.9622 - val_loss: 0.1133 - val_accuracy: 0.9626
     Epoch 3/3
-    328/328 - 52s - loss: 0.0677 - accuracy: 0.9738 - val_loss: 0.2039 - val_accuracy: 0.9384
+    328/328 - 52s - loss: 0.0672 - accuracy: 0.9744 - val_loss: 0.1073 - val_accuracy: 0.9645
 
-    <keras.callbacks.History object at 0x7f852d70ec50>
+    <keras.callbacks.History object at 0x7fbd81ee4990>
 
 
 
@@ -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:** ( 5 minutes  19.204 seconds)
+   **Total running time of the script:** ( 5 minutes  16.541 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 621934146..c0f3f2424 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
 =================
-**06:12.563** total execution time for **how_to_work_with_microtvm** files:
+**06:10.763** total execution time for **how_to_work_with_microtvm** files:
 
 +---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``)               | 05:19.204 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``)               | 05:16.541 | 0.0 MB |
 +---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)         | 00:41.884 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)         | 00:42.695 | 0.0 MB |
 +---------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``)                   | 00:08.181 | 0.0 MB |
 +---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)             | 00:03.292 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)             | 00:03.345 | 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 e8698f6d8..5b1e3d837 100644
--- a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
 
 Computation times
 =================
-**00:42.596** total execution time for **how_to_work_with_relay** files:
+**00:43.397** 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``) | 00:31.170 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:31.859 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)           | 00:09.924 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)           | 00:10.002 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)                             | 00:01.495 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)                             | 00:01.528 | 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 c92a4fc36..7ea5a3ffd 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 0x7f84b34479e0>
+    <function my_cuda_math_rule at 0x7fbd6c08ae60>
 
 
 
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 fab62aece..289c1a6fe 100644
--- a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
@@ -5,22 +5,22 @@
 
 Computation times
 =================
-**00:04.085** total execution time for **how_to_work_with_schedules** files:
+**00:04.128** total execution time for **how_to_work_with_schedules** files:
 
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)                 | 00:01.872 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)                 | 00:01.915 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)                     | 00:00.990 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)                     | 00:00.973 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)                     | 00:00.530 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)                     | 00:00.534 | 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``)                               | 00:00.520 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)                     | 00:00.098 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)                     | 00:00.103 | 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``) | 00:00.042 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)                               | 00:00.027 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)                               | 00:00.028 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``)               | 00:00.015 | 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 63dfbda35..62b68a3e6 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/tmpzx77doff/input0.cc'\nsource_filename = \"/tmp/tmpzx77doff/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/tmpgx188lzl/input0.cc'\nsource_filename = \"/tmp/tmpgx188lzl/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 89af7a05a..bf06a806c 100644
--- a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
 
 Computation times
 =================
-**00:20.922** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:22.155** total execution time for **topic_vta_tutorials_autotvm** files:
 
 +---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:20.916 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:22.148 | 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 1784a385a..6add574ed 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 22.65s!
+    resnet18_v1 inference graph built in 23.99s!
 
 
 
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 a365eab06..8e995b907 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -335,7 +335,7 @@ The compilation steps are:
       "target_host parameter is going to be deprecated. "
     /workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
       DeprecationWarning,
-    yolov3-tiny inference graph built in 15.83s!
+    yolov3-tiny inference graph built in 16.49s!
 
 
 
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 a9f439ee1..3dfa093f6 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
 =================
-**01:32.264** total execution time for **topic_vta_tutorials_frontend** files:
+**01:36.542** total execution time for **topic_vta_tutorials_frontend** files:
 
 +------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)           | 00:49.379 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)           | 00:52.220 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:42.885 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:44.322 | 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 38412b5bf..dc760c146 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
 =================
-**00:03.261** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.265** total execution time for **topic_vta_tutorials_optimize** files:
 
 +--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)         | 00:02.861 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)         | 00:02.857 | 0.0 MB |
 +--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.400 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.408 | 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 0fc7762ef..fd10c21e2 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
 =================
-**00:00.721** total execution time for **topic_vta_tutorials** files:
+**00:00.741** total execution time for **topic_vta_tutorials** files:
 
 +---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.388 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.398 | 0.0 MB |
 +---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.333 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.343 | 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 1e478a17c..140279d3a 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -326,7 +326,7 @@ We build the binary and check its correctness and performance.
 
  .. code-block:: none
 
-    Execution time of this operator: 93.111 ms
+    Execution time of this operator: 93.482 ms
 
 
 
@@ -442,6 +442,11 @@ Expression (TE) language that demonstrates how TVM can optimize computational
 operations.
 
 
+.. rst-class:: sphx-glr-timing
+
+   **Total running time of the script:** ( 1 minutes  5.729 seconds)
+
+
 .. _sphx_glr_download_tutorial_auto_scheduler_matmul_x86.py:
 
 .. only:: html
diff --git a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
index a780a3291..32b400e09 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: 10.59/10.59     result: MeasureResult(costs=(0.0253470342,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5390493869781494, timestamp=1661453325.3026946)       [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
-    No: 2   GFLOPS: 2.95/10.59      result: MeasureResult(costs=(0.09090695480000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6036720275878906, timestamp=1661453326.9196548)        [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
-    No: 3   GFLOPS: 11.84/11.84     result: MeasureResult(costs=(0.0226681616,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.560218095779419, timestamp=1661453327.9701195)        [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
-    No: 4   GFLOPS: 1.59/11.84      result: MeasureResult(costs=(0.1689274108,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.821287155151367, timestamp=1661453330.8371866)        [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
-    No: 5   GFLOPS: 3.61/11.84      result: MeasureResult(costs=(0.07433205940000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3297615051269531, timestamp=1661453332.29576)  [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
-    No: 6   GFLOPS: 1.53/11.84      result: MeasureResult(costs=(0.1760127394,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.936185121536255, timestamp=1661453335.8039503)        [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
-    No: 7   GFLOPS: 0.82/11.84      result: MeasureResult(costs=(0.327365736,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.3547515869140625, timestamp=1661453341.7317622)        [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
-    No: 8   GFLOPS: 9.89/11.84      result: MeasureResult(costs=(0.0271289766,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5759289264678955, timestamp=1661453342.3274128)       [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
-    No: 9   GFLOPS: 1.61/11.84      result: MeasureResult(costs=(0.1666052774,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.781675338745117, timestamp=1661453345.2292595)        [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
-    No: 10  GFLOPS: 2.53/11.84      result: MeasureResult(costs=(0.106263207,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8240606784820557, timestamp=1661453347.0911853)        [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+    No: 1   GFLOPS: 8.82/8.82       result: MeasureResult(costs=(0.030417669599999995,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.629288911819458, timestamp=1661452775.4720354)        [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+    No: 2   GFLOPS: 2.13/8.82       result: MeasureResult(costs=(0.12575622960000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1732444763183594, timestamp=1661452777.6570754)        [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+    No: 3   GFLOPS: 11.74/11.74     result: MeasureResult(costs=(0.0228570148,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5562417507171631, timestamp=1661452778.725979)        [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+    No: 4   GFLOPS: 1.85/11.74      result: MeasureResult(costs=(0.1448999166,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4421818256378174, timestamp=1661452781.751723)        [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+    No: 5   GFLOPS: 3.58/11.74      result: MeasureResult(costs=(0.07503549579999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3387136459350586, timestamp=1661452783.2224953)        [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+    No: 6   GFLOPS: 1.77/11.74      result: MeasureResult(costs=(0.1513502148,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5829274654388428, timestamp=1661452785.848455)        [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+    No: 7   GFLOPS: 0.88/11.74      result: MeasureResult(costs=(0.3066290516,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.025393486022949, timestamp=1661452791.4603856)        [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+    No: 8   GFLOPS: 10.03/11.74     result: MeasureResult(costs=(0.026774842599999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5797567367553711, timestamp=1661452792.0542002)       [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+    No: 9   GFLOPS: 1.75/11.74      result: MeasureResult(costs=(0.15379882279999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.563011884689331, timestamp=1661452794.736932)  [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+    No: 10  GFLOPS: 2.76/11.74      result: MeasureResult(costs=(0.0971874326,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6627240180969238, timestamp=1661452796.454875)        [('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 9979c40d1..59ef124c4 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': 499.75286977000104, 'median': 499.7251776500036, 'std': 0.6332072523480163}
+    {'mean': 496.1014442699969, 'median': 495.984946599998, 'std': 0.6595242498605052}
 
 
 
@@ -563,30 +563,30 @@ the tuning data to.
 
     /workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-
    [Task  1/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  1/25]  Current/Best:   17.52/  17.52 GFLOPS | Progress: (4/20) | 5.89 s
    [Task  1/25]  Current/Best:    6.14/  17.52 GFLOPS | Progress: (8/20) | 9.48 s
    [Task  1/25]  Current/Best:   11.53/  22.73 GFLOPS | Progress: (12/20) | 11.96 s
    [Task  1/25]  Current/Best:   16.44/  22.73 GFLOPS | Progress: (16/20) | 13.65 s
    [Task  1/25]  Current/Best:   11.58/  23.78 GFLOPS | Progress: (20/20) | 15.41 s Done.
-
    [Task  2/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  2/25]  Current/Best:   12.19/  13.19 GFLOPS | Progress: (4/20) | 3.82 s
    [Task  2/25]  Current/Best:   14.15/  17.89 GFLOPS | Progress: (8/20) | 5.12 s
    [Task  2/25]  Current/Best:   21.05/  21.05 GFLOPS | Progress: (12/20) | 6.45 s
    [Task  2/25]  Current/Best:   12.51/  21.05 GFLOPS | Progress: (16/20) | 7.73 s
    [Task  2/25]  Current/Best:   19.89/  21.05 GFLOPS | Progress: (20/20) | 9.36 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/  10.80 GFLOPS | Progress: (4/20) | 5.89 s
    [Task  3/25]  Current/Best:   15.28/  16.72 GFLOPS | Progress: (8/20) | 7.84 s
    [Task  3/25]  Current/Best:   15.00/  16.72 GFLOPS | Progress: (12/20) | 9.55 s
    [Task  3/25]  Current/Best:    7.19/  23.73 GFLOPS | Progress: (16/20) | 11.47 s
    [Task  3/25]  Current/Best:   12.64/  23.73 GFLOPS | Progress: (20/20) | 16.04 s Done.
-
    [Task  4/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  4/25]  Current/Best:    9.51/  19.82 GFLOPS | Progress: (4/20) | 2.41 s
    [Task  4/25]  Current/Best:    6.80/  19.82 GFLOPS | Progress: (8/20) | 7.16 s
    [Task  4/25]  Current/Best:   22.15/  22.15 GFLOPS | Progress: (12/20) | 12.17 s
    [Task  4/25]  Current/Best:   16.87/  22.15 GFLOPS | Progress: (16/20) | 14.58 s
    [Task  4/25]  Current/Best:   13.35/  22.15 GFLOPS | Progress: (20/20) | 16.65 s Done.
-
    [Task  5/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  5/25]  Current/Best:    9.49/  10.17 GFLOPS | Progress: (4/20) | 2.61 s
    [Task  5/25]  Current/Best:   11.60/  12.86 GFLOPS | Progress: (8/20) | 4.69 s
    [Task  5/25]  Current/Best:   11.20/  18.05 GFLOPS | Progress: (12/20) | 7.94 s
    [Task  5/25]  Current/Best:   11.62/  22.50 GFLOPS | Progress: (16/20) | 9.40 s
    [Task  5/25]  Current/Best:   12.04/  22.50 GFLOPS | Progress: (20/20) | 11.31 s Done.
-
    [Task  6/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  6/25]  Current/Best:   12.20/  20.80 GFLOPS | Progress: (4/20) | 4.14 s
    [Task  6/25]  Current/Best:   18.94/  20.80 GFLOPS | Progress: (8/20) | 5.92 s
    [Task  6/25]  Current/Best:   12.64/  20.80 GFLOPS | Progress: (12/20) | 7.89 s
    [Task  6/25]  Current/Best:   19.99/  20.80 GFLOPS | Progress: (16/20) | 10.17 s
    [Task  6/25]  Current/Best:    3.71/  20.80 GFLOPS | Progress: (20/20) | 12.68 s Done.
-
    [Task  7/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  7/25]  Current/Best:   11.13/  12.95 GFLOPS | Progress: (4/20) | 3.59 s
    [Task  7/25]  Current/Best:   20.23/  21.16 GFLOPS | Progress: (8/20) | 5.11 s
    [Task  7/25]  Current/Best:   16.02/  21.16 GFLOPS | Progress: (12/20) | 7.04 s
    [Task  7/25]  Current/Best:   12.22/  21.16 GFLOPS | Progress: (16/20) | 9.09 s
    [Task  7/25]  Current/Best:    6.38/  21.75 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:    9.77/  13.95 GFLOPS | Progress: (4/20) | 2.95 s
    [Task  8/25]  Current/Best:    9.32/  13.95 GFLOPS | Progress: (8/20) | 8.16 s
    [Task  8/25]  Current/Best:   12.74/  13.95 GFLOPS | Progress: (12/20) | 14.67 s
    [Task  8/25]  Current/Best:   18.96/  18.96 GFLOPS | Progress: (16/20) | 16.78 s
    [Task  8/25]  Current/Best:   19.39/  19.39 GFLOPS | Progress: (20/20) | 24.01 s Done.
-
    [Task  9/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  9/25]  Current/Best:   14.36/  15.71 GFLOPS | Progress: (4/20) | 11.96 s
    [Task  9/25]  Current/Best:   23.41/  23.41 GFLOPS | Progress: (8/20) | 13.78 s
    [Task  9/25]  Current/Best:    8.26/  23.41 GFLOPS | Progress: (12/20) | 16.36 s
    [Task  9/25]  Current/Best:   16.38/  23.41 GFLOPS | Progress: (16/20) | 19.26 s
    [Task  9/25]  Current/Best:    9.22/  23.41 GFLOPS | Progress: (20/20) | 27.89 s
    [Task 10/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 10/25]  Current/Best:   18.23/  18.23 GFLOPS | Progress: (4/20) | 2.57 s
    [Task 10/25]  Current/Best:   15.52/  18.23 GFLOPS | Progress: (8/20) | 4.20 s
    [Task 10/25]  Current/Best:   12.21/  18.96 GFLOPS | Progress: (12/20) | 5.76 s
    [Task 10/25]  Current/Best:   19.10/  20.22 GFLOPS | Progress: (16/20) | 6.87 s
    [Task 10/25]  Current/Best:    8.90/  20.22 GFLOPS | Progress: (20/20
 ) | 8.42 s Done.
-
    [Task 11/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 11/25]  Current/Best:   12.32/  18.13 GFLOPS | Progress: (4/20) | 3.43 s
    [Task 11/25]  Current/Best:   16.92/  18.13 GFLOPS | Progress: (8/20) | 6.26 s
    [Task 11/25]  Current/Best:   18.06/  18.13 GFLOPS | Progress: (12/20) | 8.32 s
    [Task 11/25]  Current/Best:   13.51/  20.98 GFLOPS | Progress: (16/20) | 11.28 s
    [Task 11/25]  Current/Best:   19.38/  21.50 GFLOPS | Progress: (20/20) | 13.39 s Done.
-
    [Task 12/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 12/25]  Current/Best:    7.79/  18.38 GFLOPS | Progress: (4/20) | 5.79 s
    [Task 12/25]  Current/Best:    5.27/  18.38 GFLOPS | Progress: (8/20) | 9.78 s
    [Task 12/25]  Current/Best:   18.63/  18.85 GFLOPS | Progress: (12/20) | 11.77 s
    [Task 12/25]  Current/Best:   15.29/  18.85 GFLOPS | Progress: (16/20) | 14.74 s
    [Task 12/25]  Current/Best:   15.22/  18.94 GFLOPS | Progress: (20/20) | 16.68 s Done.
-
    [Task 13/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 13/25]  Current/Best:    8.56/  17.41 GFLOPS | Progress: (4/20) | 3.83 s
    [Task 13/25]  Current/Best:   15.12/  20.93 GFLOPS | Progress: (8/20) | 6.47 s
    [Task 13/25]  Current/Best:   19.72/  21.59 GFLOPS | Progress: (12/20) | 9.51 s
    [Task 13/25]  Current/Best:   12.23/  21.59 GFLOPS | Progress: (16/20) | 13.00 s
    [Task 13/25]  Current/Best:   18.39/  21.59 GFLOPS | Progress: (20/20) | 15.35 s Done.
-
    [Task 14/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 14/25]  Current/Best:   13.56/  13.56 GFLOPS | Progress: (4/20) | 3.45 s
    [Task 14/25]  Current/Best:    6.08/  13.56 GFLOPS | Progress: (8/20) | 5.64 s
    [Task 14/25]  Current/Best:   20.24/  20.24 GFLOPS | Progress: (12/20) | 8.31 s
    [Task 14/25]  Current/Best:   16.70/  20.24 GFLOPS | Progress: (16/20) | 9.98 s Done.
-
    [Task 14/25]  Current/Best:   17.37/  20.24 GFLOPS | Progress: (20/20) | 11.73 s
    [Task 15/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 15/25]  Current/Best:   16.21/  17.63 GFLOPS | Progress: (4/20) | 2.73 s
    [Task 15/25]  Current/Best:   13.26/  18.08 GFLOPS | Progress: (8/20) | 4.07 s
    [Task 15/25]  Current/Best:   10.38/  22.34 GFLOPS | Progress: (12/20) | 6.36 s
    [Task 15/25]  Current/Best:   20.43/  22.34 GFLOPS | Progress: (16/20) | 9.41 s
    [Task 15/25]  Current/Best:    9.71/  22.34 GFLOPS | Progress: (20/20) | 10.42 s
    [Task 16/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 16/25]  Current/Best:   20.31/  20.31 GFLOPS | Progress: (4/20) | 2.97 s
    [Task 16/25]  Current/Best:    2.97/  20.31 GFLOPS | Progress: (8/20) | 4.60 s
    [Task 16/25]  Current/Best:   19.15/  20.31 GFLOPS | Progress: (12/20) | 5.81 s
    [Task 16/25]  Current/Best:   17.72/  20.31 GFLOPS | Progress: (16/20) |
  7.20 s
    [Task 16/25]  Current/Best:    9.95/  21.85 GFLOPS | Progress: (20/20) | 9.40 s Done.
-
    [Task 17/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 17/25]  Current/Best:   12.82/  16.77 GFLOPS | Progress: (4/20) | 4.85 s
    [Task 17/25]  Current/Best:   13.13/  23.24 GFLOPS | Progress: (8/20) | 7.74 s
    [Task 17/25]  Current/Best:   17.13/  23.24 GFLOPS | Progress: (12/20) | 9.80 s
    [Task 17/25]  Current/Best:   16.64/  23.24 GFLOPS | Progress: (16/20) | 12.06 s
    [Task 17/25]  Current/Best:   10.05/  23.24 GFLOPS | Progress: (20/20) | 14.21 s Done.
-
    [Task 18/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 18/25]  Current/Best:   11.37/  18.08 GFLOPS | Progress: (4/20) | 3.83 s
    [Task 18/25]  Current/Best:   10.55/  18.08 GFLOPS | Progress: (8/20) | 7.60 s
    [Task 18/25]  Current/Best:   18.99/  18.99 GFLOPS | Progress: (12/20) | 9.55 s
    [Task 18/25]  Current/Best:    9.99/  18.99 GFLOPS | Progress: (16/20) | 13.46 s
    [Task 18/25]  Current/Best:   20.55/  20.55 GFLOPS | Progress: (20/20) | 14.99 s Done.
-
    [Task 19/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 19/25]  Current/Best:    7.16/  20.45 GFLOPS | Progress: (4/20) | 6.18 s
    [Task 19/25]  Current/Best:    2.69/  20.45 GFLOPS | Progress: (8/20) | 9.50 s
    [Task 19/25]  Current/Best:   20.07/  20.45 GFLOPS | Progress: (12/20) | 12.56 s
    [Task 19/25]  Current/Best:   14.41/  21.45 GFLOPS | Progress: (16/20) | 15.60 s
    [Task 19/25]  Current/Best:    2.70/  22.84 GFLOPS | Progress: (20/20) | 18.39 s Done.
-
    [Task 20/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 20/25]  Current/Best:   10.23/  15.22 GFLOPS | Progress: (4/20) | 3.35 s Done.
+
    [Task  1/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  1/25]  Current/Best:   17.44/  17.44 GFLOPS | Progress: (4/20) | 5.97 s
    [Task  1/25]  Current/Best:    6.15/  17.44 GFLOPS | Progress: (8/20) | 9.55 s
    [Task  1/25]  Current/Best:   11.49/  22.77 GFLOPS | Progress: (12/20) | 12.07 s
    [Task  1/25]  Current/Best:   16.51/  22.77 GFLOPS | Progress: (16/20) | 13.77 s
    [Task  1/25]  Current/Best:   11.50/  23.89 GFLOPS | Progress: (20/20) | 15.56 s Done.
+
    [Task  2/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  2/25]  Current/Best:   12.14/  13.10 GFLOPS | Progress: (4/20) | 3.98 s
    [Task  2/25]  Current/Best:   14.14/  18.56 GFLOPS | Progress: (8/20) | 5.30 s
    [Task  2/25]  Current/Best:   20.81/  20.81 GFLOPS | Progress: (12/20) | 6.63 s
    [Task  2/25]  Current/Best:   12.22/  20.81 GFLOPS | Progress: (16/20) | 7.94 s
    [Task  2/25]  Current/Best:   20.28/  20.81 GFLOPS | Progress: (20/20) | 9.58 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/  10.81 GFLOPS | Progress: (4/20) | 5.89 s
    [Task  3/25]  Current/Best:   15.26/  16.70 GFLOPS | Progress: (8/20) | 7.85 s
    [Task  3/25]  Current/Best:   14.96/  16.70 GFLOPS | Progress: (12/20) | 9.57 s
    [Task  3/25]  Current/Best:    7.15/  23.51 GFLOPS | Progress: (16/20) | 11.52 s
    [Task  3/25]  Current/Best:   12.52/  23.51 GFLOPS | Progress: (20/20) | 16.11 s Done.
+
    [Task  4/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  4/25]  Current/Best:    9.39/  19.65 GFLOPS | Progress: (4/20) | 2.45 s
    [Task  4/25]  Current/Best:    6.82/  19.65 GFLOPS | Progress: (8/20) | 7.26 s
    [Task  4/25]  Current/Best:   21.15/  21.15 GFLOPS | Progress: (12/20) | 12.31 s
    [Task  4/25]  Current/Best:   16.99/  21.15 GFLOPS | Progress: (16/20) | 14.76 s
    [Task  4/25]  Current/Best:   13.42/  21.15 GFLOPS | Progress: (20/20) | 16.73 s Done.
+
    [Task  5/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  5/25]  Current/Best:    9.80/  10.38 GFLOPS | Progress: (4/20) | 2.61 s
    [Task  5/25]  Current/Best:   11.85/  13.09 GFLOPS | Progress: (8/20) | 4.67 s
    [Task  5/25]  Current/Best:   11.02/  18.16 GFLOPS | Progress: (12/20) | 7.91 s
    [Task  5/25]  Current/Best:   11.92/  22.52 GFLOPS | Progress: (16/20) | 9.33 s
    [Task  5/25]  Current/Best:   12.01/  22.52 GFLOPS | Progress: (20/20) | 11.21 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/  20.79 GFLOPS | Progress: (4/20) | 4.18 s
    [Task  6/25]  Current/Best:   18.98/  20.79 GFLOPS | Progress: (8/20) | 5.94 s
    [Task  6/25]  Current/Best:   13.26/  20.79 GFLOPS | Progress: (12/20) | 7.91 s
    [Task  6/25]  Current/Best:   19.79/  20.79 GFLOPS | Progress: (16/20) | 10.16 s
    [Task  6/25]  Current/Best:    3.75/  20.79 GFLOPS | Progress: (20/20) | 12.67 s Done.
+
    [Task  7/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  7/25]  Current/Best:   11.13/  12.78 GFLOPS | Progress: (4/20) | 3.68 s
    [Task  7/25]  Current/Best:   20.11/  21.05 GFLOPS | Progress: (8/20) | 5.22 s
    [Task  7/25]  Current/Best:   13.20/  21.05 GFLOPS | Progress: (12/20) | 7.21 s
    [Task  7/25]  Current/Best:   12.27/  21.05 GFLOPS | Progress: (16/20) | 9.25 s
    [Task  7/25]  Current/Best:    6.32/  21.55 GFLOPS | Progress: (20/20) | 11.73 s Done.
+
    [Task  8/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  8/25]  Current/Best:   10.12/  14.46 GFLOPS | Progress: (4/20) | 2.95 s
    [Task  8/25]  Current/Best:    9.61/  14.46 GFLOPS | Progress: (8/20) | 8.12 s
    [Task  8/25]  Current/Best:   12.68/  14.46 GFLOPS | Progress: (12/20) | 14.76 s
    [Task  8/25]  Current/Best:   18.96/  18.96 GFLOPS | Progress: (16/20) | 16.86 s
    [Task  8/25]  Current/Best:   20.30/  20.30 GFLOPS | Progress: (20/20) | 24.03 s Done.
+
    [Task  9/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  9/25]  Current/Best:   14.26/  15.73 GFLOPS | Progress: (4/20) | 11.99 s
    [Task  9/25]  Current/Best:   22.95/  22.95 GFLOPS | Progress: (8/20) | 13.80 s
    [Task  9/25]  Current/Best:    8.21/  22.95 GFLOPS | Progress: (12/20) | 16.38 s
    [Task  9/25]  Current/Best:   17.90/  22.95 GFLOPS | Progress: (16/20) | 19.28 s
    [Task  9/25]  Current/Best:    9.10/  22.95 GFLOPS | Progress: (20/20) | 28.16 s
    [Task 10/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 10/25]  Current/Best:   18.26/  18.26 GFLOPS | Progress: (4/20) | 2.59 s
    [Task 10/25]  Current/Best:   15.52/  18.26 GFLOPS | Progress: (8/20) | 4.27 s
    [Task 10/25]  Current/Best:   13.44/  19.23 GFLOPS | Progress: (12/20) | 5.83 s
    [Task 10/25]  Current/Best:   18.89/  20.29 GFLOPS | Progress: (16/20) | 6.95 s
    [Task 10/25]  Current/Best:    8.85/  20.29 GFLOPS | Progress: (20/20
 ) | 8.49 s Done.
+
    [Task 11/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 11/25]  Current/Best:   12.09/  18.14 GFLOPS | Progress: (4/20) | 3.37 s
    [Task 11/25]  Current/Best:   15.00/  18.14 GFLOPS | Progress: (8/20) | 6.22 s
    [Task 11/25]  Current/Best:   18.19/  18.19 GFLOPS | Progress: (12/20) | 8.32 s
    [Task 11/25]  Current/Best:   13.49/  20.94 GFLOPS | Progress: (16/20) | 11.22 s
    [Task 11/25]  Current/Best:   19.44/  21.53 GFLOPS | Progress: (20/20) | 13.36 s Done.
+
    [Task 12/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 12/25]  Current/Best:    7.76/  17.97 GFLOPS | Progress: (4/20) | 5.88 s
    [Task 12/25]  Current/Best:    5.24/  17.97 GFLOPS | Progress: (8/20) | 9.86 s
    [Task 12/25]  Current/Best:   18.96/  19.02 GFLOPS | Progress: (12/20) | 11.88 s
    [Task 12/25]  Current/Best:   15.39/  19.02 GFLOPS | Progress: (16/20) | 14.83 s
    [Task 12/25]  Current/Best:   15.19/  19.02 GFLOPS | Progress: (20/20) | 16.76 s Done.
+
    [Task 13/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 13/25]  Current/Best:    8.43/  17.30 GFLOPS | Progress: (4/20) | 3.84 s
    [Task 13/25]  Current/Best:   15.16/  20.91 GFLOPS | Progress: (8/20) | 6.49 s
    [Task 13/25]  Current/Best:   19.57/  21.71 GFLOPS | Progress: (12/20) | 9.54 s
    [Task 13/25]  Current/Best:   12.25/  21.71 GFLOPS | Progress: (16/20) | 13.01 s
    [Task 13/25]  Current/Best:   18.70/  21.71 GFLOPS | Progress: (20/20) | 15.31 s Done.
+
    [Task 14/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 14/25]  Current/Best:   13.63/  13.63 GFLOPS | Progress: (4/20) | 3.39 s
    [Task 14/25]  Current/Best:    6.12/  13.63 GFLOPS | Progress: (8/20) | 5.57 s
    [Task 14/25]  Current/Best:   20.61/  20.61 GFLOPS | Progress: (12/20) | 8.27 s
    [Task 14/25]  Current/Best:   16.85/  20.61 GFLOPS | Progress: (16/20) | 9.95 s Done.
+
    [Task 14/25]  Current/Best:   17.18/  20.61 GFLOPS | Progress: (20/20) | 11.71 s
    [Task 15/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 15/25]  Current/Best:   16.15/  17.64 GFLOPS | Progress: (4/20) | 2.76 s
    [Task 15/25]  Current/Best:   14.40/  18.03 GFLOPS | Progress: (8/20) | 4.09 s
    [Task 15/25]  Current/Best:   10.37/  22.25 GFLOPS | Progress: (12/20) | 6.37 s
    [Task 15/25]  Current/Best:   20.38/  22.25 GFLOPS | Progress: (16/20) | 9.63 s
    [Task 15/25]  Current/Best:    9.69/  22.25 GFLOPS | Progress: (20/20) | 10.65 s
    [Task 16/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 16/25]  Current/Best:   20.32/  20.32 GFLOPS | Progress: (4/20) | 3.04 s
    [Task 16/25]  Current/Best:    3.03/  20.32 GFLOPS | Progress: (8/20) | 4.67 s
    [Task 16/25]  Current/Best:   19.29/  20.32 GFLOPS | Progress: (12/20) | 5.90 s
    [Task 16/25]  Current/Best:   17.95/  20.32 GFLOPS | Progress: (16/20) |
  7.31 s
    [Task 16/25]  Current/Best:   10.03/  21.93 GFLOPS | Progress: (20/20) | 9.48 s Done.
+
    [Task 17/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 17/25]  Current/Best:   13.26/  18.52 GFLOPS | Progress: (4/20) | 4.84 s
    [Task 17/25]  Current/Best:   13.79/  22.93 GFLOPS | Progress: (8/20) | 7.65 s
    [Task 17/25]  Current/Best:   17.78/  22.93 GFLOPS | Progress: (12/20) | 9.72 s
    [Task 17/25]  Current/Best:   16.36/  22.93 GFLOPS | Progress: (16/20) | 11.97 s
    [Task 17/25]  Current/Best:    9.94/  22.93 GFLOPS | Progress: (20/20) | 14.16 s Done.
+
    [Task 18/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 18/25]  Current/Best:   11.40/  17.48 GFLOPS | Progress: (4/20) | 3.87 s
    [Task 18/25]  Current/Best:   10.61/  20.00 GFLOPS | Progress: (8/20) | 7.59 s
    [Task 18/25]  Current/Best:   19.52/  20.00 GFLOPS | Progress: (12/20) | 9.51 s
    [Task 18/25]  Current/Best:    9.98/  20.00 GFLOPS | Progress: (16/20) | 13.41 s
    [Task 18/25]  Current/Best:   20.33/  20.33 GFLOPS | Progress: (20/20) | 14.93 s Done.
+
    [Task 19/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 19/25]  Current/Best:    6.80/  20.27 GFLOPS | Progress: (4/20) | 6.22 s
    [Task 19/25]  Current/Best:    2.69/  20.27 GFLOPS | Progress: (8/20) | 9.53 s
    [Task 19/25]  Current/Best:   19.79/  20.97 GFLOPS | Progress: (12/20) | 12.48 s
    [Task 19/25]  Current/Best:   14.53/  20.97 GFLOPS | Progress: (16/20) | 15.53 s
    [Task 19/25]  Current/Best:    2.70/  22.99 GFLOPS | Progress: (20/20) | 18.36 s Done.
+
    [Task 20/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 20/25]  Current/Best:    9.16/  15.12 GFLOPS | Progress: (4/20) | 3.41 s Done.
      Done.
-
    [Task 20/25]  Current/Best:   10.51/  15.22 GFLOPS | Progress: (8/20) | 6.87 s
    [Task 20/25]  Current/Best:    2.34/  16.71 GFLOPS | Progress: (12/20) | 10.80 s
    [Task 20/25]  Current/Best:   12.29/  16.71 GFLOPS | Progress: (16/20) | 14.79 s
    [Task 20/25]  Current/Best:   12.58/  21.88 GFLOPS | Progress: (20/20) | 16.89 s
    [Task 21/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 21/25]  Current/Best:    6.42/  17.75 GFLOPS | Progress: (4/20) | 3.32 s
    [Task 21/25]  Current/Best:   14.49/  17.75 GFLOPS | Progress: (8/20) | 4.87 s
    [Task 21/25]  Current/Best:    1.61/  17.75 GFLOPS | Progress: (12/20) | 6.99 s
    [Task 21/25]  Current/Best:   17.29/  17.75 GFLOPS | Progress: (16/20) | 10.54 s
    [Task 21/25]  Current/Best:    4.47/  17.75 GFLOPS | Progress: (20/20) | 17.90 s
    [Task 22/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 22/25]  Current/Best:    2.70/  16.97 GFLOPS | Progress: (4/20
 ) | 2.70 s
    [Task 22/25]  Current/Best:    8.63/  21.99 GFLOPS | Progress: (8/20) | 4.74 s
    [Task 22/25]  Current/Best:   19.92/  21.99 GFLOPS | Progress: (12/20) | 7.13 s
    [Task 22/25]  Current/Best:   15.09/  21.99 GFLOPS | Progress: (16/20) | 9.27 s
    [Task 22/25]  Current/Best:   13.97/  21.99 GFLOPS | Progress: (20/20) | 10.95 s Done.
-
    [Task 23/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 23/25]  Current/Best:   17.72/  20.89 GFLOPS | Progress: (4/20) | 3.27 s
    [Task 23/25]  Current/Best:   14.33/  20.89 GFLOPS | Progress: (8/20) | 6.64 s
    [Task 23/25]  Current/Best:   21.02/  21.80 GFLOPS | Progress: (12/20) | 8.49 s
    [Task 23/25]  Current/Best:    6.41/  21.80 GFLOPS | Progress: (16/20) | 15.59 s
    [Task 23/25]  Current/Best:    7.96/  21.80 GFLOPS | Progress: (20/20) | 19.79 s Done.
-
    [Task 24/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 24/25]  Current/Best:    8.27/   8.27 GFLOPS | Progress: (4/20) | 11.83 s
    [Task 24/25]  Current/Best:    2.13/   8.27 GFLOPS | Progress: (8/20) | 22.90 s
    [Task 24/25]  Current/Best:    4.10/   8.27 GFLOPS | Progress: (12/20) | 34.43 s Done.
-
    [Task 24/25]  Current/Best:    6.26/   8.74 GFLOPS | Progress: (16/20) | 40.14 s
    [Task 24/25]  Current/Best:    3.40/   8.74 GFLOPS | Progress: (20/20) | 46.19 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/   2.88 GFLOPS | Progress: (4/20) | 11.59 s
    [Task 25/25]  Current/Best:    5.99/   8.24 GFLOPS | Progress: (8/20) | 22.90 s
    [Task 25/25]  Current/Best:    6.03/   8.24 GFLOPS | Progress: (12/20) | 34.40 s
    [Task 25/25]  Current/Best:    5.85/   8.77 GFLOPS | Progress: (16/20) | 36.15 s
    [Task 25/25]  Current/Best:    2.87/   9.26 GFLOPS | Progress: (20/20) | 46.82 s
+
    [Task 20/25]  Current/Best:   10.37/  15.12 GFLOPS | Progress: (8/20) | 6.83 s
    [Task 20/25]  Current/Best:    2.33/  16.59 GFLOPS | Progress: (12/20) | 10.72 s
    [Task 20/25]  Current/Best:   11.05/  16.59 GFLOPS | Progress: (16/20) | 14.53 s
    [Task 20/25]  Current/Best:   13.54/  21.81 GFLOPS | Progress: (20/20) | 16.63 s
    [Task 21/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 21/25]  Current/Best:    6.39/  17.65 GFLOPS | Progress: (4/20) | 3.34 s
    [Task 21/25]  Current/Best:   14.52/  17.65 GFLOPS | Progress: (8/20) | 4.95 s
    [Task 21/25]  Current/Best:    1.61/  17.65 GFLOPS | Progress: (12/20) | 7.13 s
    [Task 21/25]  Current/Best:   17.98/  17.98 GFLOPS | Progress: (16/20) | 10.73 s
    [Task 21/25]  Current/Best:    4.45/  17.98 GFLOPS | Progress: (20/20) | 18.22 s
    [Task 22/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 22/25]  Current/Best:    2.70/  16.96 GFLOPS | Progress: (4/20
 ) | 2.74 s
    [Task 22/25]  Current/Best:    9.15/  21.83 GFLOPS | Progress: (8/20) | 4.74 s
    [Task 22/25]  Current/Best:   19.81/  21.83 GFLOPS | Progress: (12/20) | 7.17 s
    [Task 22/25]  Current/Best:   15.34/  21.83 GFLOPS | Progress: (16/20) | 9.33 s
    [Task 22/25]  Current/Best:   14.91/  21.83 GFLOPS | Progress: (20/20) | 11.08 s Done.
+
    [Task 23/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 23/25]  Current/Best:   17.34/  20.28 GFLOPS | Progress: (4/20) | 3.30 s
    [Task 23/25]  Current/Best:   14.94/  20.28 GFLOPS | Progress: (8/20) | 6.71 s
    [Task 23/25]  Current/Best:   20.75/  21.24 GFLOPS | Progress: (12/20) | 8.58 s
    [Task 23/25]  Current/Best:    5.94/  21.24 GFLOPS | Progress: (16/20) | 15.83 s
    [Task 23/25]  Current/Best:    7.27/  21.24 GFLOPS | Progress: (20/20) | 20.13 s Done.
+
    [Task 24/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 24/25]  Current/Best:    8.66/   8.66 GFLOPS | Progress: (4/20) | 11.86 s
    [Task 24/25]  Current/Best:    2.12/   8.66 GFLOPS | Progress: (8/20) | 22.89 s
    [Task 24/25]  Current/Best:    4.26/   8.66 GFLOPS | Progress: (12/20) | 34.49 s Done.
+
    [Task 24/25]  Current/Best:    6.75/   8.66 GFLOPS | Progress: (16/20) | 40.27 s
    [Task 24/25]  Current/Best:    3.30/   8.69 GFLOPS | Progress: (20/20) | 46.39 s Done.
+
    [Task 25/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 25/25]  Current/Best:    1.54/   2.88 GFLOPS | Progress: (4/20) | 11.64 s
    [Task 25/25]  Current/Best:    5.65/   7.89 GFLOPS | Progress: (8/20) | 22.96 s
    [Task 25/25]  Current/Best:    5.62/   7.89 GFLOPS | Progress: (12/20) | 34.47 s
    [Task 25/25]  Current/Best:    5.70/   9.22 GFLOPS | Progress: (16/20) | 36.45 s
    [Task 25/25]  Current/Best:    2.89/   9.22 GFLOPS | Progress: (20/20) | 47.13 s
 
 
 
@@ -748,8 +748,8 @@ improvement in comparing the optimized model to the unoptimized model.
 
  .. code-block:: none
 
-    optimized: {'mean': 407.3998885199967, 'median': 407.39381009999533, 'std': 0.6752243425527152}
-    unoptimized: {'mean': 499.75286977000104, 'median': 499.7251776500036, 'std': 0.6332072523480163}
+    optimized: {'mean': 413.2848333200059, 'median': 413.1303025999955, 'std': 0.7787494950685662}
+    unoptimized: {'mean': 496.1014442699969, 'median': 495.984946599998, 'std': 0.6595242498605052}
 
 
 
@@ -772,7 +772,7 @@ profiling/benchmarking.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 10 minutes  31.391 seconds)
+   **Total running time of the script:** ( 10 minutes  34.685 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 a4232ef15..47962226a 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
 
-    1.283e-07 secs/op
+    1.272e-07 secs/op
 
 
 
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 92ea000ba..bcda3ab43 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, 0x19a5c3f0)), stage(b, placeholder(b, 0x43f50f0)), 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, 0xbe94460)), stage(b, placeholder(b, 0x99bb6d0)), 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 01495a2bb..f9a27a363 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,28 +5,28 @@
 
 Computation times
 =================
-**13:26.266** total execution time for **tutorial** files:
+**13:38.222** total execution time for **tutorial** files:
 
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)                 | 10:31.391 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)                 | 10:34.685 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)     | 01:00.956 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:05.729 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 00:55.627 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)     | 00:59.935 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)                 | 00:30.825 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)                 | 00:31.247 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)               | 00:25.269 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)               | 00:24.625 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)       | 00:01.350 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)       | 00:01.131 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)                               | 00:00.698 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)                               | 00:00.706 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.142 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.156 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``)                           | 00:00.005 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``)                                             | 00:00.002 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``)                                             | 00:00.001 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``)   | 00:00.001 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 684795329..84c86cc81 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: 0.000009
-    naive: 0.000007
+    Numpy running time: 0.000007
+    naive: 0.000006
 
 
 
@@ -460,7 +460,7 @@ factor to be the number of threads on your CPU.
 
     /workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-    vector: 0.000026
+    vector: 0.000025
     @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    8.653610000237678e-06                    1.0
-                   naive              6.7228e-06      0.7768780890074031
-                parallel              6.0385e-06      0.6978012644242285
-                  vector    2.6289899999999997e-05    3.0380269042951933
+                   numpy    7.0908500015320895e-06                   1.0
+                   naive              5.8344e-06      0.8228068565460257
+                parallel               6.161e-06       0.868866214723033
+                  vector    2.4562899999999998e-05    3.4640275840968004
 
 
 
@@ -936,7 +936,7 @@ matrix multiplication.
 
  .. code-block:: none
 
-    Numpy running time: 0.018314
+    Numpy running time: 0.018526
 
 
 
@@ -996,7 +996,7 @@ optimizations.
 
     /workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-    none: 3.438344
+    none: 3.307796
 
 
 
@@ -1101,7 +1101,7 @@ schedule.
 
     /workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-    blocking: 0.286687
+    blocking: 0.314472
 
 
 
@@ -1199,7 +1199,7 @@ already cache friendly from our previous optimizations.
 
     /workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-    vectorization: 0.323368
+    vectorization: 0.348802
     @main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
       attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
       buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1275,7 +1275,7 @@ more cache friendly.
 
     /workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-    loop permutation: 0.117042
+    loop permutation: 0.117619
     @main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
       attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
       buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1376,7 +1376,7 @@ optimized schedule.
 
     /workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-    array packing: 0.110127
+    array packing: 0.108992
     @main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
       attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
       buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1471,7 +1471,7 @@ to `C` when all the block results are ready.
 
     /workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-    block caching: 0.110493
+    block caching: 0.110536
     @main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
       attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
       buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1559,7 +1559,7 @@ of thread-level parallelization.
 
     /workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-    parallelization: 0.146466
+    parallelization: 0.146337
     @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      3.4383444901000004                     1.0
-                blocking     0.28668711139999997     0.08337940314749032
-           vectorization            0.3233684449     0.09404771564660619
-        loop permutation     0.11704175829999999     0.03404014886728118
-           array packing     0.11012749070000001    0.032029219590151384
-           block caching            0.1104934692    0.032135659913700626
-         parallelization     0.14646577460000001     0.04259776035290176
+                    none            3.3077962892                     1.0
+                blocking            0.3144722179     0.09507000746290092
+           vectorization     0.34880158790000004     0.10544832795140438
+        loop permutation     0.11761856560000002     0.03555798341754788
+           array packing     0.10899163969999999     0.03294992501680324
+           block caching     0.11053564180000001    0.033416701675644415
+         parallelization            0.1463374053     0.04424015039190703
 
 
 
@@ -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  0.956 seconds)
-
-
 .. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
 
 .. only:: html
diff --git a/docs/commit_hash b/docs/commit_hash
index f160ac245..4624107a8 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-01fcdfcf5fcfda313df4e176ca3d919b076f77fc
+bb00a15c265ba12341aede06bbbf216dda585211
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index ee2a351d3..bd031e9c1 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  8.367 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  10.152 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 5bb7833dc..dfd076116 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.zipc60e9b81-d247-4e47-9712-9da971d27eeb 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.zip2e1302a3-6b30-47de-9cd9-5e36ad7d5de1 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 979ef4606..d504d3d30 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -432,14 +432,14 @@ 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]
- 19%|#9        | 7.99M/41.5M [00:00&lt;00:00, 40.3MB/s]
- 35%|###4      | 14.3M/41.5M [00:00&lt;00:01, 27.4MB/s]
- 41%|####1     | 17.1M/41.5M [00:00&lt;00:00, 27.0MB/s]
- 54%|#####3    | 22.3M/41.5M [00:00&lt;00:00, 32.4MB/s]
- 63%|######3   | 26.3M/41.5M [00:00&lt;00:00, 34.9MB/s]
- 77%|#######7  | 32.0M/41.5M [00:00&lt;00:00, 39.8MB/s]
- 92%|#########2| 38.3M/41.5M [00:01&lt;00:00, 40.8MB/s]
-100%|##########| 41.5M/41.5M [00:01&lt;00:00, 36.3MB/s]
+ 15%|#5        | 6.33M/41.5M [00:00&lt;00:01, 35.2MB/s]
+ 23%|##3       | 9.69M/41.5M [00:00&lt;00:01, 25.7MB/s]
+ 35%|###4      | 14.3M/41.5M [00:00&lt;00:00, 32.4MB/s]
+ 43%|####2     | 17.7M/41.5M [00:00&lt;00:00, 26.8MB/s]
+ 58%|#####7    | 24.0M/41.5M [00:00&lt;00:00, 30.5MB/s]
+ 82%|########2 | 34.1M/41.5M [00:00&lt;00:00, 46.8MB/s]
+ 97%|#########7| 40.4M/41.5M [00:01&lt;00:00, 51.6MB/s]
+100%|##########| 41.5M/41.5M [00:01&lt;00:00, 41.1MB/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 03df8a16d..26784bac5 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]
- 45%|####4     | 19.9M/44.7M [00:00&lt;00:00, 208MB/s]
- 89%|########9 | 39.8M/44.7M [00:00&lt;00:00, 196MB/s]
-100%|##########| 44.7M/44.7M [00:00&lt;00:00, 191MB/s]
+ 39%|###9      | 17.5M/44.7M [00:00&lt;00:00, 184MB/s]
+ 98%|#########7| 43.7M/44.7M [00:00&lt;00:00, 237MB/s]
+100%|##########| 44.7M/44.7M [00:00&lt;00:00, 230MB/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 90f2fdea0..ea2f42946 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  2.116 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  3.303 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 9e119b5d3..55dfeb8e7 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>05:09.887</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:14.806</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 81%" />
@@ -336,43 +336,43 @@
 </colgroup>
 <tbody>
 <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>01:08.367</p></td>
+<td><p>01:10.152</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <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>01:02.116</p></td>
+<td><p>01:03.303</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>00:39.739</p></td>
+<td><p>00:40.153</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>00:28.295</p></td>
+<td><p>00:28.392</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>00:25.662</p></td>
+<td><p>00:25.581</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>00:25.409</p></td>
+<td><p>00:24.680</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>00:22.219</p></td>
+<td><p>00:23.267</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>00:19.599</p></td>
+<td><p>00:20.311</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="from_keras.html#sphx-glr-how-to-compile-models-from-keras-py"><span class="std std-ref">Compile Keras Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_keras.py</span></code>)</p></td>
-<td><p>00:15.675</p></td>
+<td><p>00:16.521</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>00:02.805</p></td>
+<td><p>00:02.444</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 1421456e3..f3f4dada1 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)
-  15.9978      15.9742      16.2668      15.8427       0.1235
+  16.6787      16.4114      17.3335      16.1247       0.5068
 </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 026500645..127ebb6c8 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -436,14 +436,14 @@ 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]
-  9%|9         | 15.3M/170M [00:00&lt;00:01, 160MB/s]
- 23%|##2       | 38.7M/170M [00:00&lt;00:00, 210MB/s]
- 36%|###5      | 61.0M/170M [00:00&lt;00:00, 219MB/s]
- 49%|####8     | 82.9M/170M [00:00&lt;00:00, 224MB/s]
- 65%|######4   | 110M/170M [00:00&lt;00:00, 245MB/s]
- 80%|#######9  | 135M/170M [00:00&lt;00:00, 251MB/s]
- 96%|#########6| 163M/170M [00:00&lt;00:00, 266MB/s]
-100%|##########| 170M/170M [00:00&lt;00:00, 245MB/s]
+ 10%|9         | 16.4M/170M [00:00&lt;00:00, 172MB/s]
+ 23%|##2       | 38.9M/170M [00:00&lt;00:00, 209MB/s]
+ 38%|###7      | 63.9M/170M [00:00&lt;00:00, 234MB/s]
+ 52%|#####2    | 88.6M/170M [00:00&lt;00:00, 244MB/s]
+ 67%|######6   | 113M/170M [00:00&lt;00:00, 249MB/s]
+ 81%|########1 | 138M/170M [00:00&lt;00:00, 251MB/s]
+ 95%|#########5| 162M/170M [00:00&lt;00:00, 236MB/s]
+100%|##########| 170M/170M [00:00&lt;00:00, 237MB/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;).
@@ -538,7 +538,7 @@ torchvision rcnn models.</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  1.285 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  3.307 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 196d40f73..5010eb301 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -480,8 +480,7 @@ training. Other models require a full post training calibration.</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: &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]
- 76%|#######6  | 10.3M/13.6M [00:00&lt;00:00, 108MB/s]
-100%|##########| 13.6M/13.6M [00:00&lt;00:00, 114MB/s]
+100%|##########| 13.6M/13.6M [00:00&lt;00:00, 164MB/s]
 </pre></div>
 </div>
 </div>
@@ -570,7 +569,7 @@ 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)
-  90.3389      90.2780      95.2355      90.0115       0.5432
+  90.3940      90.2899      95.7821      90.0619       0.5797
 </pre></div>
 </div>
 <div class="admonition note">
@@ -609,7 +608,7 @@ 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  10.505 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  10.791 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 399d81e1c..b7e505bcd 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)
-  121.2638     121.1995     122.8537     120.5858      0.3461
+  121.9901     121.9944     122.6127     121.3698      0.2601
 </pre></div>
 </div>
 <div class="admonition note">
@@ -601,7 +601,7 @@ network for ARM CPU</span></a>.</p></li>
 </ul>
 </div></blockquote>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes  0.142 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes  0.221 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 848516ce8..9cf386745 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  43.057 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  35.068 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 0c29c045f..63efaebfe 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -441,24 +441,23 @@ to your device.</p>
 Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
 
   0%|          | 0/132723 [00:00&lt;?, ?KB/s]
-  5%|4         | 6405/132723 [00:00&lt;00:01, 64045.33KB/s]
- 11%|#         | 14532/132723 [00:00&lt;00:01, 74174.00KB/s]
- 17%|#7        | 22786/132723 [00:00&lt;00:01, 77989.05KB/s]
- 23%|##3       | 31062/132723 [00:00&lt;00:01, 79870.53KB/s]
- 29%|##9       | 39050/132723 [00:00&lt;00:01, 63817.47KB/s]
- 36%|###5      | 47259/132723 [00:00&lt;00:01, 69142.96KB/s]
- 41%|####1     | 54541/132723 [00:00&lt;00:01, 65836.39KB/s]
- 47%|####7     | 62694/132723 [00:00&lt;00:00, 70269.61KB/s]
- 53%|#####3    | 70953/132723 [00:00&lt;00:00, 73811.13KB/s]
- 60%|#####9    | 79237/132723 [00:01&lt;00:00, 76437.62KB/s]
- 66%|######5   | 87029/132723 [00:01&lt;00:00, 63661.69KB/s]
- 72%|#######1  | 95203/132723 [00:01&lt;00:00, 68322.92KB/s]
- 77%|#######7  | 102424/132723 [00:01&lt;00:00, 47108.49KB/s]
- 83%|########2 | 109911/132723 [00:01&lt;00:00, 52856.76KB/s]
- 88%|########7 | 116240/132723 [00:01&lt;00:00, 50030.85KB/s]
- 93%|#########3| 123697/132723 [00:01&lt;00:00, 55624.53KB/s]
- 99%|#########8| 131117/132723 [00:02&lt;00:00, 60186.94KB/s]
-100%|##########| 132723/132723 [00:02&lt;00:00, 63026.76KB/s]
+  5%|5         | 6779/132723 [00:00&lt;00:01, 67785.38KB/s]
+ 11%|#1        | 14829/132723 [00:00&lt;00:01, 75259.86KB/s]
+ 17%|#7        | 22863/132723 [00:00&lt;00:01, 77577.29KB/s]
+ 23%|##3       | 31028/132723 [00:00&lt;00:01, 79181.53KB/s]
+ 29%|##9       | 38947/132723 [00:00&lt;00:01, 55828.76KB/s]
+ 35%|###5      | 47017/132723 [00:00&lt;00:01, 62452.77KB/s]
+ 41%|####1     | 54794/132723 [00:00&lt;00:01, 66673.58KB/s]
+ 47%|####7     | 62861/132723 [00:00&lt;00:00, 70625.36KB/s]
+ 53%|#####3    | 71000/132723 [00:01&lt;00:00, 73718.42KB/s]
+ 60%|#####9    | 79170/132723 [00:01&lt;00:00, 76040.28KB/s]
+ 66%|######5   | 87012/132723 [00:01&lt;00:00, 61985.91KB/s]
+ 72%|#######1  | 95085/132723 [00:01&lt;00:00, 66730.06KB/s]
+ 77%|#######7  | 102250/132723 [00:01&lt;00:00, 56886.75KB/s]
+ 83%|########3 | 110335/132723 [00:01&lt;00:00, 62656.00KB/s]
+ 89%|########9 | 118414/132723 [00:01&lt;00:00, 67296.60KB/s]
+ 95%|#########5| 126414/132723 [00:01&lt;00:00, 70696.38KB/s]
+100%|##########| 132723/132723 [00:01&lt;00:00, 68049.58KB/s]
 </pre></div>
 </div>
 <p>Create TVM runtime and do inference
@@ -501,7 +500,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
 <span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
 </pre></div>
 </div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes  35.223 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  43.432 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 c749cb10c..03e2123bb 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>11:45.414</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>11:49.860</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>03:01.285</p></td>
+<td><p>03:03.307</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>02:35.223</p></td>
+<td><p>02:43.432</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized_tflite.html#sphx-glr-how-to-deploy-models-deploy-prequantized-tflite-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite)</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized_tflite.py</span></code>)</p></td>
-<td><p>02:00.142</p></td>
+<td><p>02:00.221</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>01:43.057</p></td>
+<td><p>01:35.068</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>01:10.505</p></td>
+<td><p>01:10.791</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>00:29.822</p></td>
+<td><p>00:30.587</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>00:22.872</p></td>
+<td><p>00:23.488</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:22.500</p></td>
+<td><p>00:22.959</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 d7a9430b3..6162c1317 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.zip0f41d8d6-03f1-40d0-89d9-2a446b83a0b3 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.zip1d4bd40c-67ea-4037-8527-382c77200cde from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
 </pre></div>
 </div>
 <p>It’s easy to execute MobileNet with native TVM:</p>
diff --git a/docs/how_to/extend_tvm/sg_execution_times.html b/docs/how_to/extend_tvm/sg_execution_times.html
index 097f93e76..56f8d3f35 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>00:40.844</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:42.229</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 84%" />
@@ -336,19 +336,19 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:37.653</p></td>
+<td><p>00:38.986</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>00:02.201</p></td>
+<td><p>00:02.265</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="use_pass_infra.html#sphx-glr-how-to-extend-tvm-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></td>
-<td><p>00:00.983</p></td>
+<td><p>00:00.969</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
-<td><p>00:00.007</p></td>
+<td><p>00:00.008</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 </tbody>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 566050cc9..9542200e6 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: 7142us [7142us] (46.78%; 46.78%)
-FoldScaleAxis: 8127us [7us] (53.22%; 53.22%)
-        FoldConstant: 8120us [1722us] (53.18%; 99.92%)
-                InferType: 6398us [6398us] (41.90%; 78.79%)
+InferType: 6815us [6815us] (46.32%; 46.32%)
+FoldScaleAxis: 7898us [6us] (53.68%; 53.68%)
+        FoldConstant: 7892us [1632us] (53.64%; 99.93%)
+                InferType: 6260us [6260us] (42.55%; 79.32%)
 </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: 6599us [6599us] (45.03%; 45.03%)
-FoldScaleAxis: 8054us [6us] (54.97%; 54.97%)
-        FoldConstant: 8049us [1684us] (54.93%; 99.93%)
-                InferType: 6365us [6365us] (43.43%; 79.08%)
+InferType: 6304us [6304us] (44.65%; 44.65%)
+FoldScaleAxis: 7816us [5us] (55.35%; 55.35%)
+        FoldConstant: 7811us [1615us] (55.32%; 99.94%)
+                InferType: 6196us [6196us] (43.88%; 79.33%)
 </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 219d46d7e..26f6b5753 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: 54.143767 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.200517 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 451f1d813..ea31b4e86 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: 6.650397 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 6.578599 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 81cbf432d..9d67f3753 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: 0.018469
-Baseline: 3.422294
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019346
+Baseline: 3.307523
 </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: 0.297363
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.316917
 </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: 0.332500
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.343967
 </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: 0.115016
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.120405
 </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: 0.110444
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109842
 </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: 0.111119
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111244
 </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: 0.146974
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.147428
 </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 b573388cb..8c40e9ad8 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>00:34.416</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.619</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>00:32.222</p></td>
+<td><p>00:32.437</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>00:01.202</p></td>
+<td><p>00:01.204</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>00:00.992</p></td>
+<td><p>00:00.978</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 e5665388b..4fa4e5cc7 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>06:15.371</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>06:09.622</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>03:17.525</p></td>
+<td><p>03:19.356</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>01:22.050</p></td>
+<td><p>01:24.177</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>00:46.881</p></td>
+<td><p>00:47.595</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>00:31.268</p></td>
+<td><p>00:20.481</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>00:08.992</p></td>
+<td><p>00:09.077</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>00:08.654</p></td>
+<td><p>00:08.936</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 92dda0e65..36f8e98d1 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
@@ -491,483 +491,38 @@ 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, [4]), storage_scope = local;
-  allocate(pad_temp.shared: Pointer(shared float32), float32, [1568]), storage_scope = shared;
-  allocate(kernel.shared: Pointer(shared float32), float32, [512]), storage_scope = shared;
-  attr [IterVar(threadIdx.x: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 196 {
-    conv2d_nchw_1: Buffer(conv2d_nchw, float32, [1], [], scope=&quot;local&quot;, align=4)[0] = 0f32
-    conv2d_nchw_1[1] = 0f32
-    conv2d_nchw_1[2] = 0f32
-    conv2d_nchw_1[3] = 0f32
+  attr [IterVar(blockIdx.x: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;blockIdx.x&quot;)] &quot;thread_extent&quot; = 64;
+  allocate(conv2d_nchw: Pointer(local float32), float32, [7]), storage_scope = local;
+  allocate(pad_temp.shared: Pointer(shared float32), float32, [2016]), storage_scope = shared;
+  allocate(kernel.shared: Pointer(shared float32), float32, [768]), storage_scope = shared;
+  attr [IterVar(threadIdx.x: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56 {
+    for (yy.inner.init: int32, 0, 7) {
+      conv2d_nchw_1: Buffer(conv2d_nchw, float32, [7], [], scope=&quot;local&quot;, align=16)[yy.inner.init] = 0f32
+    }
     for (rc.outer.outer: int32, 0, 16) {
-      for (ry.outer.outer: int32, 0, 3) {
-        let cse_var_2: int32 = (rc.outer.outer*288)
-        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; = 196;
-          pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1568], [], scope=&quot;shared&quot;)[threadIdx.x_1] = @tir.if_then_else((((1 &lt;= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) &amp;&amp; ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) &lt; 8)) &amp;&amp; (1 &lt;= floormod(threadIdx.x_1, 7))), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) - 8)], 0f32, dtype=float32)
-          attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 196;
-          pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else((((1 &lt;= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) &amp;&amp; ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) &lt; 8)) &amp;&amp; (1 &lt;= floormod(threadIdx.x_1, 7))), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) + 188)], 0f32, dtype=float32)
-          attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 196;
-          pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else((((1 &lt;= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) &amp;&amp; ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) &lt; 8)) &amp;&amp; (1 &lt;= floormod(threadIdx.x_1, 7))), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) + 384)], 0f32, dtype=float32)
-          attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 196;
-          pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else((((1 &lt;= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) &amp;&amp; ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) &lt; 8)) &amp;&amp; (1 &lt;= floormod(threadIdx.x_1, 7))), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) + 580)], 0f32, dtype=float32)
-          attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 196;
-          pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else((((1 &lt;= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) &amp;&amp; ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) &lt; 8)) &amp;&amp; (1 &lt;= floormod(threadIdx.x_1, 7))), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) + 776)], 0f32, dtype=float32)
-          attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 196;
-          pad_temp.shared_1[(threadIdx.x_1 + 980)] = @tir.if_then_else((((1 &lt;= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) &amp;&amp; ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) &lt; 8)) &amp;&amp; (1 &lt;= floormod(threadIdx.x_1, 7))), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) + 972)], 0f32, dtype=float32)
-          attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 196;
-          pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else((((1 &lt;= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) &amp;&amp; ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) &lt; 8)) &amp;&amp; (1 &lt;= floormod(threadIdx.x_1, 7))), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) + 1168)], 0f32, dtype=float32)
-          attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 196;
-          pad_temp.shared_1[(threadIdx.x_1 + 1372)] = @tir.if_then_else((((1 &lt;= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) &amp;&amp; ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) &lt; 8)) &amp;&amp; (1 &lt;= floormod(threadIdx.x_1, 7))), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) + 1364)], 0f32, dtype=float32)
-          attr [IterVar(threadIdx.x_2: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 196;
-          kernel.shared_1: Buffer(kernel.shared, float32, [512], [], scope=&quot;shared&quot;)[threadIdx.x_2] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 32)*4608)) + cse_var_2) + (floormod(threadIdx.x_2, 32)*9)) + cse_var_1)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 196;
-          kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 196), 32)*4608)) + cse_var_2) + (floormod((threadIdx.x_2 + 4), 32)*9)) + cse_var_1)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 196;
-          if @tir.likely((threadIdx.x_2 &lt; 120), dtype=bool) {
-            kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 392), 32)*4608)) + cse_var_2) + (floormod((threadIdx.x_2 + 8), 32)*9)) + cse_var_1)]
-          }
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[(floordiv(threadIdx.x, 49)*32)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 128)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 256)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 384)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 1)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 129)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 257)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 385)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 2)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 130)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 258)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 386)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 3)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 131)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 259)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 387)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 4)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 132)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 260)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 388)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 5)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 133)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 261)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 389)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 6)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 134)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 262)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 390)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 7)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 135)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 263)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 391)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 8)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 136)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 264)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 392)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 9)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 137)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 265)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 393)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 10)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 138)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 266)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 394)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 11)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 139)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 267)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 395)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 12)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 140)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 268)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 396)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 13)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 141)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 269)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 397)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 14)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 142)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 270)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 398)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 15)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 143)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 271)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 399)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 784)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 16)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 784)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 144)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 784)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 272)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 784)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 400)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 833)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 17)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 833)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 145)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 833)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 273)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 833)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 401)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 882)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 18)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 882)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 146)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 882)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 274)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 882)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 402)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 931)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 19)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 931)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 147)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 931)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 275)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 931)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 403)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 980)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 20)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 980)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 148)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 980)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 276)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 980)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 404)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1029)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 21)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1029)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 149)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1029)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 277)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1029)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 405)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1078)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 22)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1078)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 150)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1078)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 278)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1078)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 406)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1127)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 23)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1127)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 151)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1127)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 279)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1127)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 407)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1176)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 24)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1176)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 152)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1176)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 280)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1176)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 408)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1225)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 25)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1225)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 153)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1225)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 281)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1225)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 409)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1274)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 26)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1274)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 154)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1274)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 282)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1274)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 410)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1323)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 27)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1323)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 155)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1323)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 283)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1323)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 411)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1372)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 28)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1372)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 156)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1372)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 284)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1372)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 412)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1421)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 29)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1421)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 157)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1421)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 285)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1421)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 413)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1470)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 30)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1470)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 158)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1470)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 286)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1470)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 414)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1519)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 31)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1519)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 159)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1519)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 287)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1519)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 415)]))
-          attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 196;
-          pad_temp.shared_1[threadIdx.x_1] = @tir.if_then_else(((1 &lt;= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) &amp;&amp; ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) &lt; 8)), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) - 7)], 0f32, dtype=float32)
-          attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 196;
-          pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((1 &lt;= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) &amp;&amp; ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) &lt; 8)), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) + 189)], 0f32, dtype=float32)
-          attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 196;
-          pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((1 &lt;= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) &amp;&amp; ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) &lt; 8)), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) + 385)], 0f32, dtype=float32)
-          attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 196;
-          pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else(((1 &lt;= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) &amp;&amp; ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) &lt; 8)), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) + 581)], 0f32, dtype=float32)
-          attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 196;
-          pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((1 &lt;= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) &amp;&amp; ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) &lt; 8)), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) + 777)], 0f32, dtype=float32)
-          attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 196;
-          pad_temp.shared_1[(threadIdx.x_1 + 980)] = @tir.if_then_else(((1 &lt;= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) &amp;&amp; ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) &lt; 8)), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) + 973)], 0f32, dtype=float32)
-          attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 196;
-          pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((1 &lt;= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) &amp;&amp; ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) &lt; 8)), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) + 1169)], 0f32, dtype=float32)
-          attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 196;
-          pad_temp.shared_1[(threadIdx.x_1 + 1372)] = @tir.if_then_else(((1 &lt;= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) &amp;&amp; ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) &lt; 8)), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) + 1365)], 0f32, dtype=float32)
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 196;
-          kernel.shared_1[threadIdx.x_2] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 32)*4608)) + cse_var_2) + (floormod(threadIdx.x_2, 32)*9)) + cse_var_1) + 1)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 196;
-          kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 196), 32)*4608)) + cse_var_2) + (floormod((threadIdx.x_2 + 4), 32)*9)) + cse_var_1) + 1)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 196;
-          if @tir.likely((threadIdx.x_2 &lt; 120), dtype=bool) {
-            kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 392), 32)*4608)) + cse_var_2) + (floormod((threadIdx.x_2 + 8), 32)*9)) + cse_var_1) + 1)]
+      for (rx.outer.outer: int32, 0, 3) {
+        for (ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer: int32, 0, 36) {
+          attr [IterVar(threadIdx.x_1: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
+          pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2016], [], scope=&quot;shared&quot;)[((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_1)] = @tir.if_then_else(((((1 &lt;= floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*8) + floordiv(threadIdx.x_1, 7)), 9)) &amp;&amp; (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*8) + floordiv(threadIdx.x_1, 7)), 9) &lt; 8)) &amp;&amp; (1 &lt;= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) &amp;&amp; ( [...]
+        }
+        for (ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer_1: int32, 0, 14) {
+          attr [IterVar(threadIdx.x_2: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 56;
+          if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer_1*7) + floordiv(threadIdx.x_2, 8)) &lt; 96), dtype=bool) {
+            kernel.shared_1: Buffer(kernel.shared, float32, [768], [], scope=&quot;shared&quot;)[((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer_1*56) + threadIdx.x_2)] = kernel[((((((blockIdx.x*36864) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer_1*7) + floordiv(threadIdx.x_2, 8)), 12)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer_1*56) + threadIdx.x_2), 96), 3)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer. [...]
           }
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[(floordiv(threadIdx.x, 49)*32)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 128)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 256)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 384)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 1)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 129)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 257)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 385)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 2)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 130)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 258)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 386)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 3)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 131)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 259)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 387)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 4)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 132)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 260)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 388)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 5)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 133)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 261)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 389)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 6)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 134)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 262)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 390)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 7)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 135)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 263)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 391)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 8)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 136)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 264)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 392)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 9)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 137)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 265)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 393)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 10)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 138)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 266)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 394)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 11)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 139)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 267)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 395)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 12)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 140)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 268)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 396)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 13)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 141)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 269)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 397)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 14)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 142)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 270)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 398)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 15)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 143)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 271)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 399)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 784)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 16)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 784)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 144)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 784)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 272)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 784)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 400)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 833)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 17)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 833)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 145)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 833)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 273)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 833)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 401)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 882)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 18)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 882)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 146)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 882)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 274)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 882)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 402)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 931)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 19)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 931)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 147)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 931)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 275)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 931)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 403)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 980)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 20)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 980)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 148)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 980)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 276)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 980)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 404)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1029)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 21)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1029)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 149)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1029)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 277)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1029)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 405)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1078)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 22)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1078)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 150)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1078)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 278)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1078)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 406)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1127)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 23)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1127)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 151)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1127)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 279)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1127)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 407)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1176)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 24)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1176)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 152)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1176)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 280)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1176)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 408)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1225)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 25)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1225)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 153)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1225)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 281)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1225)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 409)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1274)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 26)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1274)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 154)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1274)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 282)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1274)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 410)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1323)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 27)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1323)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 155)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1323)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 283)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1323)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 411)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1372)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 28)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1372)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 156)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1372)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 284)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1372)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 412)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1421)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 29)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1421)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 157)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1421)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 285)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1421)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 413)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1470)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 30)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1470)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 158)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1470)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 286)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1470)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 414)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1519)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 31)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1519)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 159)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1519)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 287)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1519)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 415)]))
-          attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 196;
-          pad_temp.shared_1[threadIdx.x_1] = @tir.if_then_else((((1 &lt;= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) &amp;&amp; ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) &lt; 8)) &amp;&amp; (floormod(threadIdx.x_1, 7) &lt; 6)), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) - 6)], 0f32, dtype=float32)
-          attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 196;
-          pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else((((1 &lt;= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) &amp;&amp; ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) &lt; 8)) &amp;&amp; (floormod(threadIdx.x_1, 7) &lt; 6)), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) + 190)], 0f32, dtype=float32)
-          attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 196;
-          pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else((((1 &lt;= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) &amp;&amp; ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) &lt; 8)) &amp;&amp; (floormod(threadIdx.x_1, 7) &lt; 6)), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) + 386)], 0f32, dtype=float32)
-          attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 196;
-          pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else((((1 &lt;= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) &amp;&amp; ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) &lt; 8)) &amp;&amp; (floormod(threadIdx.x_1, 7) &lt; 6)), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) + 582)], 0f32, dtype=float32)
-          attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 196;
-          pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else((((1 &lt;= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) &amp;&amp; ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) &lt; 8)) &amp;&amp; (floormod(threadIdx.x_1, 7) &lt; 6)), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) + 778)], 0f32, dtype=float32)
-          attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 196;
-          pad_temp.shared_1[(threadIdx.x_1 + 980)] = @tir.if_then_else((((1 &lt;= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) &amp;&amp; ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) &lt; 8)) &amp;&amp; (floormod(threadIdx.x_1, 7) &lt; 6)), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) + 974)], 0f32, dtype=float32)
-          attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 196;
-          pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else((((1 &lt;= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) &amp;&amp; ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) &lt; 8)) &amp;&amp; (floormod(threadIdx.x_1, 7) &lt; 6)), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) + 1170)], 0f32, dtype=float32)
-          attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 196;
-          pad_temp.shared_1[(threadIdx.x_1 + 1372)] = @tir.if_then_else((((1 &lt;= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) &amp;&amp; ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) &lt; 8)) &amp;&amp; (floormod(threadIdx.x_1, 7) &lt; 6)), data[((((rc.outer.outer*1568) + (ry.outer.outer*7)) + threadIdx.x_1) + 1366)], 0f32, dtype=float32)
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 196;
-          kernel.shared_1[threadIdx.x_2] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 32)*4608)) + cse_var_2) + (floormod(threadIdx.x_2, 32)*9)) + cse_var_1) + 2)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 196;
-          kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 196), 32)*4608)) + cse_var_2) + (floormod((threadIdx.x_2 + 4), 32)*9)) + cse_var_1) + 2)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 196;
-          if @tir.likely((threadIdx.x_2 &lt; 120), dtype=bool) {
-            kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 392), 32)*4608)) + cse_var_2) + (floormod((threadIdx.x_2 + 8), 32)*9)) + cse_var_1) + 2)]
+        }
+        for (ry.outer.inner: int32, 0, 3) {
+          for (rc.inner: int32, 0, 32) {
+            for (yy.inner: int32, 0, 7) {
+              conv2d_nchw_1[yy.inner] = (conv2d_nchw_1[yy.inner] + (pad_temp.shared_1[((((rc.inner*63) + (yy.inner*7)) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.inner*3)) + ry.outer.inner)]))
+            }
           }
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[(floordiv(threadIdx.x, 49)*32)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 128)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 256)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 384)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 1)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 129)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 257)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 385)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 2)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 130)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 258)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 386)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 3)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 131)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 259)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 387)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 4)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 132)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 260)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 388)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 5)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 133)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 261)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 389)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 6)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 134)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 262)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 390)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 7)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 135)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 263)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 391)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 8)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 136)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 264)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 392)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 9)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 137)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 265)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 393)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 10)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 138)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 266)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 394)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 11)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 139)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 267)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 395)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 12)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 140)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 268)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 396)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 13)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 141)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 269)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 397)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 14)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 142)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 270)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 398)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 15)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 143)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 271)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 399)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 784)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 16)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 784)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 144)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 784)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 272)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 784)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 400)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 833)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 17)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 833)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 145)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 833)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 273)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 833)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 401)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 882)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 18)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 882)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 146)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 882)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 274)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 882)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 402)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 931)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 19)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 931)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 147)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 931)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 275)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 931)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 403)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 980)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 20)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 980)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 148)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 980)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 276)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 980)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 404)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1029)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 21)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1029)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 149)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1029)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 277)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1029)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 405)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1078)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 22)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1078)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 150)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1078)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 278)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1078)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 406)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1127)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 23)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1127)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 151)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1127)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 279)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1127)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 407)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1176)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 24)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1176)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 152)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1176)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 280)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1176)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 408)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1225)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 25)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1225)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 153)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1225)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 281)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1225)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 409)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1274)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 26)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1274)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 154)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1274)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 282)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1274)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 410)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1323)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 27)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1323)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 155)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1323)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 283)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1323)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 411)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1372)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 28)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1372)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 156)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1372)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 284)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1372)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 412)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1421)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 29)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1421)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 157)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1421)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 285)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1421)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 413)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1470)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 30)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1470)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 158)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1470)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 286)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1470)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 414)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1519)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 31)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1519)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 159)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1519)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 287)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1519)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 415)]))
         }
       }
     }
-    compute[((blockIdx.x*784) + threadIdx.x)] = max((conv2d_nchw_1[0] + bias[((blockIdx.x*16) + floordiv(threadIdx.x, 49))]), 0f32)
-    compute[(((blockIdx.x*784) + threadIdx.x) + 196)] = max((conv2d_nchw_1[1] + bias[(((blockIdx.x*16) + floordiv(threadIdx.x, 49)) + 4)]), 0f32)
-    compute[(((blockIdx.x*784) + threadIdx.x) + 392)] = max((conv2d_nchw_1[2] + bias[(((blockIdx.x*16) + floordiv(threadIdx.x, 49)) + 8)]), 0f32)
-    compute[(((blockIdx.x*784) + threadIdx.x) + 588)] = max((conv2d_nchw_1[3] + bias[(((blockIdx.x*16) + floordiv(threadIdx.x, 49)) + 12)]), 0f32)
+    for (i2.inner: int32, 0, 7) {
+      compute[((((blockIdx.x*392) + (floordiv(threadIdx.x, 7)*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[i2.inner] + bias[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
+    }
   }
 }
 </pre></div>
@@ -1003,7 +558,7 @@ 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: 0.234 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.379 ms
 </pre></div>
 </div>
 </div>
@@ -1034,20 +589,20 @@ conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_
 conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
 conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
 conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=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=4)
-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=4)
-conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, 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=7)
 conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
-conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=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=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=16)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=32)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
 conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
-conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
+conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
 conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
 conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
 s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
@@ -1055,10 +610,10 @@ 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=1)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=4)
-compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=4)
-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_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=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=7)
@@ -1081,14 +636,14 @@ s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread
 kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
 kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
 s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=196)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
 s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis(&quot;threadIdx.x&quot;))
 pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
 pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
 s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=196)
+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;, 0)
 s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, &quot;unroll_explicit&quot;, True)
 
 CUDA source code:
@@ -1106,451 +661,37 @@ CUDA source code:
   #define int64_t long long
   #define uint64_t unsigned long long
 #endif
-extern &quot;C&quot; __global__ void __launch_bounds__(196) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
-  float conv2d_nchw[4];
-  __shared__ float pad_temp_shared[1568];
-  __shared__ float kernel_shared[512];
-  conv2d_nchw[0] = 0.000000e+00f;
-  conv2d_nchw[1] = 0.000000e+00f;
-  conv2d_nchw[2] = 0.000000e+00f;
-  conv2d_nchw[3] = 0.000000e+00f;
+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[7];
+  __shared__ float pad_temp_shared[2016];
+  __shared__ float kernel_shared[768];
+  for (int yy_inner_init = 0; yy_inner_init &lt; 7; ++yy_inner_init) {
+    conv2d_nchw[yy_inner_init] = 0.000000e+00f;
+  }
   for (int rc_outer_outer = 0; rc_outer_outer &lt; 16; ++rc_outer_outer) {
-    for (int ry_outer_outer = 0; ry_outer_outer &lt; 3; ++ry_outer_outer) {
+    for (int rx_outer_outer = 0; rx_outer_outer &lt; 3; ++rx_outer_outer) {
       __syncthreads();
-      pad_temp_shared[((int)threadIdx.x)] = ((((1 &lt;= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) &amp;&amp; ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) &lt; 8)) &amp;&amp; (1 &lt;= (((int)threadIdx.x) % 7))) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) - 8)] : 0.000000e+00f);
-      pad_temp_shared[(((int)threadIdx.x) + 196)] = ((((1 &lt;= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) &amp;&amp; ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) &lt; 8)) &amp;&amp; (1 &lt;= (((int)threadIdx.x) % 7))) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 188)] : 0.000000e+00f);
-      pad_temp_shared[(((int)threadIdx.x) + 392)] = ((((1 &lt;= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) &amp;&amp; ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) &lt; 8)) &amp;&amp; (1 &lt;= (((int)threadIdx.x) % 7))) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 384)] : 0.000000e+00f);
-      pad_temp_shared[(((int)threadIdx.x) + 588)] = ((((1 &lt;= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) &amp;&amp; ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) &lt; 8)) &amp;&amp; (1 &lt;= (((int)threadIdx.x) % 7))) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 580)] : 0.000000e+00f);
-      pad_temp_shared[(((int)threadIdx.x) + 784)] = ((((1 &lt;= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) &amp;&amp; ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) &lt; 8)) &amp;&amp; (1 &lt;= (((int)threadIdx.x) % 7))) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 776)] : 0.000000e+00f);
-      pad_temp_shared[(((int)threadIdx.x) + 980)] = ((((1 &lt;= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) &amp;&amp; ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) &lt; 8)) &amp;&amp; (1 &lt;= (((int)threadIdx.x) % 7))) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 972)] : 0.000000e+00f);
-      pad_temp_shared[(((int)threadIdx.x) + 1176)] = ((((1 &lt;= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) &amp;&amp; ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) &lt; 8)) &amp;&amp; (1 &lt;= (((int)threadIdx.x) % 7))) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 1168)] : 0.000000e+00f);
-      pad_temp_shared[(((int)threadIdx.x) + 1372)] = ((((1 &lt;= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) &amp;&amp; ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) &lt; 8)) &amp;&amp; (1 &lt;= (((int)threadIdx.x) % 7))) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 1364)] : 0.000000e+00f);
-      kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) &gt;&gt; 5) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) &amp; 31) * 9)) + (ry_outer_outer * 3))];
-      kernel_shared[(((int)threadIdx.x) + 196)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 196) &gt;&gt; 5) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 4) &amp; 31) * 9)) + (ry_outer_outer * 3))];
-      if (((int)threadIdx.x) &lt; 120) {
-        kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) &gt;&gt; 5) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) &amp; 31) * 9)) + (ry_outer_outer * 3))];
+      for (int ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer = 0; ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer &lt; 36; ++ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer) {
+        pad_temp_shared[((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x))] = (((((1 &lt;= (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 8) + (((int)threadIdx.x) / 7)) % 9)) &amp;&amp; ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 8) + (((int)threadIdx.x) / 7)) % 9) &lt; 8)) &amp;&amp; (1 &lt;= (rx_outer_outer + (((int)threadIdx.x) % 7)))) &amp;&amp; ((rx_outer_outer + (((int)threadIdx.x) % 7)) &lt; 8)) ? data[((((((rc_outer_outer * 1568) + ((((ax0_ax1 [...]
       }
-      __syncthreads();
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[((((int)threadIdx.x) / 49) * 32)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 128)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 256)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 384)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 1)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 129)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 257)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 385)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 2)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 130)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 258)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 386)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 3)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 131)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 259)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 387)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 4)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 132)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 260)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 388)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 5)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 133)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 261)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 389)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 6)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 134)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 262)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 390)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 7)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 135)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 263)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 391)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 8)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 136)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 264)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 392)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 9)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 137)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 265)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 393)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 10)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 138)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 266)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 394)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 11)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 139)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 267)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 395)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 12)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 140)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 268)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 396)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 13)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 141)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 269)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 397)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 14)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 142)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 270)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 398)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 15)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 143)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 271)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 399)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 784)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 16)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 784)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 144)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 784)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 272)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 784)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 400)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 833)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 17)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 833)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 145)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 833)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 273)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 833)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 401)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 882)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 18)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 882)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 146)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 882)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 274)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 882)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 402)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 931)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 19)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 931)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 147)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 931)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 275)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 931)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 403)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 980)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 20)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 980)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 148)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 980)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 276)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 980)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 404)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1029)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 21)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1029)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 149)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1029)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 277)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1029)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 405)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1078)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 22)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1078)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 150)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1078)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 278)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1078)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 406)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 23)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 151)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 279)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 407)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1176)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 24)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1176)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 152)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1176)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 280)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1176)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 408)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1225)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 25)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1225)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 153)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1225)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 281)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1225)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 409)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1274)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 26)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1274)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 154)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1274)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 282)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1274)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 410)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 27)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 155)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 283)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 411)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1372)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 28)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1372)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 156)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1372)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 284)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1372)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 412)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1421)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 29)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1421)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 157)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1421)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 285)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1421)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 413)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1470)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 30)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1470)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 158)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1470)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 286)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1470)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 414)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1519)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 31)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1519)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 159)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1519)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 287)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1519)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 415)]));
-      __syncthreads();
-      pad_temp_shared[((int)threadIdx.x)] = (((1 &lt;= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) &amp;&amp; ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) &lt; 8)) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) - 7)] : 0.000000e+00f);
-      pad_temp_shared[(((int)threadIdx.x) + 196)] = (((1 &lt;= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) &amp;&amp; ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) &lt; 8)) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 189)] : 0.000000e+00f);
-      pad_temp_shared[(((int)threadIdx.x) + 392)] = (((1 &lt;= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) &amp;&amp; ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) &lt; 8)) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 385)] : 0.000000e+00f);
-      pad_temp_shared[(((int)threadIdx.x) + 588)] = (((1 &lt;= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) &amp;&amp; ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) &lt; 8)) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 581)] : 0.000000e+00f);
-      pad_temp_shared[(((int)threadIdx.x) + 784)] = (((1 &lt;= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) &amp;&amp; ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) &lt; 8)) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 777)] : 0.000000e+00f);
-      pad_temp_shared[(((int)threadIdx.x) + 980)] = (((1 &lt;= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) &amp;&amp; ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) &lt; 8)) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 973)] : 0.000000e+00f);
-      pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((1 &lt;= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) &amp;&amp; ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) &lt; 8)) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 1169)] : 0.000000e+00f);
-      pad_temp_shared[(((int)threadIdx.x) + 1372)] = (((1 &lt;= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) &amp;&amp; ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) &lt; 8)) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 1365)] : 0.000000e+00f);
-      kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) &gt;&gt; 5) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) &amp; 31) * 9)) + (ry_outer_outer * 3)) + 1)];
-      kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 196) &gt;&gt; 5) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 4) &amp; 31) * 9)) + (ry_outer_outer * 3)) + 1)];
-      if (((int)threadIdx.x) &lt; 120) {
-        kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) &gt;&gt; 5) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) &amp; 31) * 9)) + (ry_outer_outer * 3)) + 1)];
+      for (int ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 = 0; ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 &lt; 14; ++ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1) {
+        if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 * 7) + (((int)threadIdx.x) &gt;&gt; 3)) &lt; 96) {
+          kernel_shared[((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 * 56) + ((int)threadIdx.x))] = kernel[((((((((int)blockIdx.x) * 36864) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 * 7) + (((int)threadIdx.x) &gt;&gt; 3)) / 12) * 4608)) + (rc_outer_outer * 288)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 * 56) + ((int)threadIdx.x)) % 96) / 3) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 * 2) + ((int)threadIdx.x)) % 3) * 3)) + rx_outer_outer)];
+        }
       }
       __syncthreads();
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[((((int)threadIdx.x) / 49) * 32)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 128)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 256)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 384)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 1)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 129)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 257)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 385)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 2)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 130)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 258)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 386)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 3)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 131)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 259)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 387)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 4)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 132)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 260)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 388)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 5)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 133)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 261)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 389)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 6)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 134)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 262)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 390)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 7)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 135)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 263)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 391)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 8)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 136)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 264)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 392)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 9)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 137)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 265)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 393)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 10)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 138)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 266)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 394)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 11)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 139)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 267)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 395)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 12)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 140)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 268)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 396)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 13)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 141)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 269)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 397)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 14)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 142)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 270)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 398)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 15)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 143)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 271)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 399)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 784)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 16)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 784)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 144)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 784)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 272)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 784)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 400)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 833)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 17)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 833)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 145)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 833)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 273)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 833)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 401)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 882)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 18)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 882)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 146)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 882)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 274)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 882)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 402)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 931)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 19)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 931)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 147)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 931)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 275)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 931)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 403)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 980)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 20)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 980)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 148)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 980)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 276)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 980)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 404)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1029)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 21)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1029)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 149)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1029)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 277)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1029)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 405)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1078)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 22)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1078)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 150)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1078)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 278)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1078)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 406)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 23)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 151)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 279)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 407)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1176)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 24)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1176)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 152)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1176)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 280)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1176)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 408)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1225)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 25)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1225)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 153)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1225)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 281)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1225)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 409)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1274)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 26)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1274)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 154)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1274)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 282)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1274)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 410)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 27)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 155)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 283)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 411)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1372)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 28)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1372)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 156)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1372)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 284)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1372)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 412)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1421)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 29)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1421)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 157)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1421)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 285)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1421)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 413)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1470)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 30)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1470)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 158)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1470)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 286)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1470)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 414)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1519)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 31)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1519)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 159)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1519)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 287)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1519)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 415)]));
-      __syncthreads();
-      pad_temp_shared[((int)threadIdx.x)] = ((((1 &lt;= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) &amp;&amp; ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) &lt; 8)) &amp;&amp; ((((int)threadIdx.x) % 7) &lt; 6)) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) - 6)] : 0.000000e+00f);
-      pad_temp_shared[(((int)threadIdx.x) + 196)] = ((((1 &lt;= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) &amp;&amp; ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) &lt; 8)) &amp;&amp; ((((int)threadIdx.x) % 7) &lt; 6)) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 190)] : 0.000000e+00f);
-      pad_temp_shared[(((int)threadIdx.x) + 392)] = ((((1 &lt;= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) &amp;&amp; ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) &lt; 8)) &amp;&amp; ((((int)threadIdx.x) % 7) &lt; 6)) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 386)] : 0.000000e+00f);
-      pad_temp_shared[(((int)threadIdx.x) + 588)] = ((((1 &lt;= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) &amp;&amp; ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) &lt; 8)) &amp;&amp; ((((int)threadIdx.x) % 7) &lt; 6)) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 582)] : 0.000000e+00f);
-      pad_temp_shared[(((int)threadIdx.x) + 784)] = ((((1 &lt;= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) &amp;&amp; ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) &lt; 8)) &amp;&amp; ((((int)threadIdx.x) % 7) &lt; 6)) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 778)] : 0.000000e+00f);
-      pad_temp_shared[(((int)threadIdx.x) + 980)] = ((((1 &lt;= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) &amp;&amp; ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) &lt; 8)) &amp;&amp; ((((int)threadIdx.x) % 7) &lt; 6)) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 974)] : 0.000000e+00f);
-      pad_temp_shared[(((int)threadIdx.x) + 1176)] = ((((1 &lt;= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) &amp;&amp; ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) &lt; 8)) &amp;&amp; ((((int)threadIdx.x) % 7) &lt; 6)) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 1170)] : 0.000000e+00f);
-      pad_temp_shared[(((int)threadIdx.x) + 1372)] = ((((1 &lt;= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) &amp;&amp; ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) &lt; 8)) &amp;&amp; ((((int)threadIdx.x) % 7) &lt; 6)) ? data[((((rc_outer_outer * 1568) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 1366)] : 0.000000e+00f);
-      kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) &gt;&gt; 5) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) &amp; 31) * 9)) + (ry_outer_outer * 3)) + 2)];
-      kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 196) &gt;&gt; 5) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 4) &amp; 31) * 9)) + (ry_outer_outer * 3)) + 2)];
-      if (((int)threadIdx.x) &lt; 120) {
-        kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) &gt;&gt; 5) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) &amp; 31) * 9)) + (ry_outer_outer * 3)) + 2)];
+      for (int ry_outer_inner = 0; ry_outer_inner &lt; 3; ++ry_outer_inner) {
+        for (int rc_inner = 0; rc_inner &lt; 32; ++rc_inner) {
+          for (int yy_inner = 0; yy_inner &lt; 7; ++yy_inner) {
+            conv2d_nchw[yy_inner] = (conv2d_nchw[yy_inner] + (pad_temp_shared[((((rc_inner * 63) + (yy_inner * 7)) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_inner * 3)) + ry_outer_inner)]));
+          }
+        }
       }
-      __syncthreads();
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[((((int)threadIdx.x) / 49) * 32)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 128)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 256)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 384)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 1)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 129)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 257)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 385)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 2)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 130)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 258)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 386)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 3)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 131)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 259)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 387)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 4)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 132)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 260)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 388)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 5)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 133)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 261)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 389)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 6)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 134)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 262)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 390)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 7)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 135)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 263)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 391)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 8)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 136)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 264)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 392)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 9)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 137)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 265)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 393)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 10)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 138)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 266)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 394)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 11)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 139)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 267)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 395)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 12)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 140)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 268)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 396)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 13)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 141)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 269)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 397)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 14)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 142)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 270)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 398)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 15)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 143)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 271)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 399)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 784)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 16)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 784)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 144)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 784)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 272)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 784)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 400)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 833)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 17)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 833)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 145)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 833)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 273)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 833)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 401)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 882)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 18)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 882)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 146)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 882)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 274)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 882)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 402)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 931)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 19)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 931)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 147)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 931)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 275)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 931)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 403)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 980)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 20)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 980)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 148)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 980)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 276)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 980)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 404)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1029)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 21)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1029)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 149)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1029)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 277)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1029)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 405)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1078)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 22)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1078)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 150)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1078)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 278)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1078)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 406)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 23)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 151)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 279)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 407)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1176)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 24)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1176)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 152)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1176)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 280)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1176)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 408)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1225)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 25)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1225)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 153)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1225)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 281)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1225)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 409)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1274)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 26)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1274)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 154)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1274)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 282)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1274)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 410)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 27)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 155)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 283)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 411)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1372)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 28)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1372)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 156)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1372)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 284)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1372)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 412)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1421)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 29)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1421)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 157)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1421)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 285)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1421)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 413)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1470)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 30)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1470)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 158)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1470)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 286)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1470)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 414)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1519)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 31)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1519)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 159)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1519)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 287)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1519)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 415)]));
     }
   }
-  compute[((((int)blockIdx.x) * 784) + ((int)threadIdx.x))] = max((conv2d_nchw[0] + bias[((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 49))]), 0.000000e+00f);
-  compute[(((((int)blockIdx.x) * 784) + ((int)threadIdx.x)) + 196)] = max((conv2d_nchw[1] + bias[(((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 49)) + 4)]), 0.000000e+00f);
-  compute[(((((int)blockIdx.x) * 784) + ((int)threadIdx.x)) + 392)] = max((conv2d_nchw[2] + bias[(((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 49)) + 8)]), 0.000000e+00f);
-  compute[(((((int)blockIdx.x) * 784) + ((int)threadIdx.x)) + 588)] = max((conv2d_nchw[3] + bias[(((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 49)) + 12)]), 0.000000e+00f);
+  for (int i2_inner = 0; i2_inner &lt; 7; ++i2_inner) {
+    compute[((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i2_inner] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+  }
 }
 </pre></div>
 </div>
@@ -1586,7 +727,7 @@ 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  17.525 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  19.356 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 f72db2574..6669e04c1 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)
-   9.8735       9.8832       9.8939       9.8434       0.0218
+   9.8300       9.8381       9.8576       9.7945       0.0264
 </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 1e9d4a076..3eb01310a 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)
-  753.2478     753.4996     754.0394     752.2046      0.7699
+  761.9509     761.8104     762.6521     761.3901      0.5247
 </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  22.050 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  24.177 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 bae62852d..e893cd2db 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -625,14 +625,14 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
              placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
              compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
   buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
-  preflattened_buffer_map = {placeholder_8: placeholder_15: Buffer(placeholder_13, int32, [33], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), placeholder_5: placeholder_19: Buffer(placeholder_10, float32, [128, 256], [])} {
-  for (i0.outer.i1.outer.fused: int32, 0, 64) &quot;parallel&quot; {
-    allocate(compute_4: Pointer(global float32), float32, [1024]), storage_scope = global {
+  preflattened_buffer_map = {placeholder_6: placeholder_15: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_5: placeholder_19: Buffer(placeholder_10, float32, [128, 256], [])} {
+  for (i0.outer.i1.outer.fused: int32, 0, 32) &quot;parallel&quot; {
+    allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global {
       for (nb_j.inner: int32, 0, 2) {
-        for (i.inner.init: int32, 0, 32) {
+        for (i.inner.init: int32, 0, 64) {
           let cse_var_1: int32 = ((i.inner.init*32) + (nb_j.inner*16))
            {
-            compute_5: Buffer(compute_4, float32, [1024], [])[cse_var_1] = 0f32
+            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
@@ -651,11 +651,11 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
           }
         }
         for (elem_idx: int32, 0, let cse_var_2: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
-          for (i.inner: int32, 0, 32) {
+          for (i.inner: int32, 0, 64) {
             let cse_var_21: int32 = (elem_idx*16)
             let cse_var_20: int32 = ((i.inner*32) + (nb_j.inner*16))
             let cse_var_19: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
-            let cse_var_18: int32 = ((floordiv(i0.outer.i1.outer.fused, 16)*8192) + (i.inner*256))
+            let cse_var_18: int32 = ((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i.inner*256))
             let cse_var_17: int32 = (cse_var_20 + 9)
             let cse_var_16: int32 = (cse_var_20 + 8)
             let cse_var_15: int32 = (cse_var_20 + 7)
@@ -692,8 +692,8 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
           }
         }
       }
-      for (i0.inner: int32, 0, 32) {
-        let cse_var_22: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
+      for (i0.inner: int32, 0, 64) {
+        let cse_var_22: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
         compute[ramp(cse_var_22, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
       }
     }
@@ -732,7 +732,7 @@ 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: 1.769 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.861 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 aedc211b2..d329b963d 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>00:46.741</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:45.570</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 84%" />
@@ -336,7 +336,7 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:46.706</p></td>
+<td><p>00:45.534</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
diff --git a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
index d9275b189..8071d4d8c 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: 177.24/177.24   result: MeasureResult(costs=(0.0013061541555555553,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.027951955795288, timestamp=1661454568.118685)        [(&#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: 0.00/177.24     result: Traceback (most recent call last):
+No: 9   GFLOPS: 177.21/177.21   result: MeasureResult(costs=(0.0013063413,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8493096828460693, timestamp=1661454039.3630486)       [(&#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: 0.00/177.21     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: 261.00/261.00   result: MeasureResult(costs=(0.0008869829502762431,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.464146375656128, timestamp=1661454569.0188472)       [(&#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: 0.00/261.00     result: Traceback (most recent call last):
+No: 11  GFLOPS: 261.25/261.25   result: MeasureResult(costs=(0.0008861220773480661,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7522459030151367, timestamp=1661454040.2921894)      [(&#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: 0.00/261.25     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: 0.00/261.00     result: Traceback (most recent call last):
+No: 13  GFLOPS: 0.00/261.25     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: 0.00/261.00     result: Traceback (most recent call last):
+No: 14  GFLOPS: 0.00/261.25     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: 5.27/261.00     result: MeasureResult(costs=(0.04395421475,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8496427536010742, timestamp=1661454573.5394044)      [(&#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: 3.34/261.00     result: MeasureResult(costs=(0.06922530974999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.52052903175354, timestamp=1661454574.777682)   [(&#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: 0.00/261.00     result: Traceback (most recent call last):
+No: 15  GFLOPS: 5.48/261.25     result: MeasureResult(costs=(0.04225220625,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8322460651397705, timestamp=1661454044.88521)        [(&#39;tile_f&#39;, [-1, 2, 2, 8]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 4, 8]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 1)],None,5330964
+No: 16  GFLOPS: 3.36/261.25     result: MeasureResult(costs=(0.06893672225,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.58309531211853, timestamp=1661454046.1246612)        [(&#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: 0.00/261.25     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: 0.00/261.00     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: 28.14/261.00    result: MeasureResult(costs=(0.008226495357142857,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2804126739501953, timestamp=1661454585.787514)        [(&#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: 0.00/261.00     result: Traceback (most recent call last):
+No: 18  GFLOPS: 26.25/261.25    result: MeasureResult(costs=(0.008818050916666665,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1476569175720215, timestamp=1661454057.0324976)       [(&#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: 0.00/261.25     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: 0.00/261.00     result: Traceback (most recent call last):
+No: 20  GFLOPS: 0.00/261.25     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: 0.001272
+Time cost of this operator: 0.001222
 </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 e5c7b088f..a3b99a8e2 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  311.6     98.733   (1, 2, 10, 10, 3)  2       1        [311.6]
-tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       3.017     0.956    (1, 6, 10, 10)     1       1        [3.017]
-tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.982     0.311    (1, 1, 10, 10, 3)  1       1        [0.982]
-Total_time                                    -                                             315.6     -        -                  -       -        -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  310.9     98.728   (1, 2, 10, 10, 3)  2       1        [310.9]
+tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       3.027     0.961    (1, 6, 10, 10)     1       1        [3.027]
+tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.977     0.31     (1, 1, 10, 10, 3)  1       1        [0.977]
+Total_time                                    -                                             314.904   -        -                  -       -        -
 </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  326.4     98.699   (1, 2, 10, 10, 3)  2       1        [326.4]
-tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       3.174     0.96     (1, 6, 10, 10)     1       1        [3.174]
-tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         1.129     0.341    (1, 1, 10, 10, 3)  1       1        [1.129]
-Total_time                                    -                                             330.702   -        -                  -       -        -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  79.812    96.694   (1, 6, 10, 10, 1)  2       1        [79.812]
+tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       1.752     2.123    (1, 6, 10, 10)     1       1        [1.752]
+tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.976     1.183    (1, 1, 10, 10, 3)  1       1        [0.976]
+Total_time                                    -                                             82.541    -        -                  -       -        -
 </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 9118ddf7f..8fb49816a 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/tmptk7s37ws/images/random&#39;
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>&#39;/tmp/tmpox6otj9z/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/tmptk7s37ws/images/target contains 8144 images
-/tmp/tmptk7s37ws/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/tmpox6otj9z/images/target contains 8144 images
+/tmp/tmpox6otj9z/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: 0.2190 - accuracy: 0.9256 - val_loss: 0.1405 - val_accuracy: 0.9588
+328/328 - 56s - loss: 0.2119 - accuracy: 0.9289 - val_loss: 0.1397 - val_accuracy: 0.9539
 Epoch 2/3
-328/328 - 52s - loss: 0.0992 - accuracy: 0.9636 - val_loss: 0.1139 - val_accuracy: 0.9637
+328/328 - 52s - loss: 0.0976 - accuracy: 0.9622 - val_loss: 0.1133 - val_accuracy: 0.9626
 Epoch 3/3
-328/328 - 52s - loss: 0.0677 - accuracy: 0.9738 - val_loss: 0.2039 - val_accuracy: 0.9384
+328/328 - 52s - loss: 0.0672 - accuracy: 0.9744 - val_loss: 0.1073 - val_accuracy: 0.9645
 
-&lt;keras.callbacks.History object at 0x7f852d70ec50&gt;
+&lt;keras.callbacks.History object at 0x7fbd81ee4990&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> ( 5 minutes  19.204 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes  16.541 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 a13c8d9bb..f10835b10 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>06:12.563</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>06:10.763</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 83%" />
@@ -336,11 +336,11 @@
 </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>05:19.204</p></td>
+<td><p>05:16.541</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>00:41.884</p></td>
+<td><p>00:42.695</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>
@@ -348,7 +348,7 @@
 <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>00:03.292</p></td>
+<td><p>00:03.345</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 09b4208c2..efc13accf 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -327,7 +327,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:42.596</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:43.397</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>00:31.170</p></td>
+<td><p>00:31.859</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>00:09.924</p></td>
+<td><p>00:10.002</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>00:01.495</p></td>
+<td><p>00:01.528</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 9205e6e60..a8d9ef5e4 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 0x7f84b34479e0&gt;
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>&lt;function my_cuda_math_rule at 0x7fbd6c08ae60&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 bdb8b3edf..1c754039c 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>00:04.085</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:04.128</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 83%" />
@@ -336,31 +336,31 @@
 </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>00:01.872</p></td>
+<td><p>00:01.915</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="tensorize.html#sphx-glr-how-to-work-with-schedules-tensorize-py"><span class="std std-ref">Use Tensorize to Leverage Hardware Intrinsics</span></a> (<code class="docutils literal notranslate"><span class="pre">tensorize.py</span></code>)</p></td>
-<td><p>00:00.990</p></td>
+<td><p>00:00.973</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="reduction.html#sphx-glr-how-to-work-with-schedules-reduction-py"><span class="std std-ref">Reduction</span></a> (<code class="docutils literal notranslate"><span class="pre">reduction.py</span></code>)</p></td>
-<td><p>00:00.530</p></td>
+<td><p>00:00.534</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="scan.html#sphx-glr-how-to-work-with-schedules-scan-py"><span class="std std-ref">Scan and Recurrent Kernel</span></a> (<code class="docutils literal notranslate"><span class="pre">scan.py</span></code>)</p></td>
-<td><p>00:00.512</p></td>
+<td><p>00:00.520</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>00:00.098</p></td>
+<td><p>00:00.103</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>00:00.042</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>
-<td><p>00:00.027</p></td>
+<td><p>00:00.028</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index cf5c7648c..f1babf0f7 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/tmpzx77doff/input0.cc&#39;\nsource_filename = \&quot;/tmp/tmpzx77doff/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/tmpgx188lzl/input0.cc&#39;\nsource_filename = \&quot;/tmp/tmpgx188lzl/input0.cc\&quot;\ntarget datalayout = \&quot;e-m:e-i64:64-f80:128-n8:16:32:64-S128\&quot;\ntarget triple = \&quot;x86_64-pc-linux-gnu\&quot;\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n  %7 = allo [...]
   for (i, 0, 1024) {
     for (j.outer: int32, 0, 32) {
       @tir.call_extern(&quot;gemv_update&quot;, @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/install/nnpack.html b/docs/install/nnpack.html
index 3153785d7..aa2238b85 100644
--- a/docs/install/nnpack.html
+++ b/docs/install/nnpack.html
@@ -224,7 +224,17 @@
               <p class="caption" role="heading"><span class="caption-text">Getting Started</span></p>
 <ul class="current">
 <li class="toctree-l1 current"><a class="reference internal" href="index.html">Installing TVM</a><ul class="current">
-<li class="toctree-l2"><a class="reference internal" href="from_source.html">Install from Source</a></li>
+<li class="toctree-l2 current"><a class="reference internal" href="from_source.html">Install from Source</a><ul class="current">
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#developers-get-source-from-github">Developers: Get Source from Github</a></li>
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#build-the-shared-library">Build the Shared Library</a></li>
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#python-package-installation">Python Package Installation</a></li>
+<li class="toctree-l3 current"><a class="reference internal" href="from_source.html#install-contrib-libraries">Install Contrib Libraries</a><ul class="current">
+<li class="toctree-l4 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a></li>
+</ul>
+</li>
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#enable-c-tests">Enable C++ Tests</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="docker.html">Docker Images</a></li>
 <li class="toctree-l2 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a><ul>
 <li class="toctree-l3"><a class="reference internal" href="#conditions">Conditions</a></li>
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 8cff1911c..989158c08 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 9a8418bb3..5b0bebdb4 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/01fcdfcf5/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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 1d9771b33..f622c61db 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/01fcdfcf5/web/src/memory.ts#L223">memory.ts:223</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/memory.ts#L208">memory.ts:208</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/memory.ts#L312">memory.ts:312</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/memory.ts#L284">memory.ts:284</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/memory.ts#L388">memory.ts:388</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/memory.ts#L376">memory.ts:376</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/memory.ts#L267">memory.ts:267</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/memory.ts#L243">memory.ts:243</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/memory.ts#L321">memory.ts:321</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/memory.ts#L252">memory.ts:252</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/memory.ts#L359">memory.ts:359</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/memory.ts#L342">memory.ts:342</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/memory.ts#L350">memory.ts:350</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/memory.ts#L326">memory.ts:326</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/memory.ts#L363">memory.ts:363</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/memory.ts#L346">memory.ts:346</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/memory.ts#L334">memory.ts:334</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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 9614245d4..1f64242b5 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/01fcdfcf5/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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 e399dca9c..976bc3a93 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/01fcdfcf5/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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 19bc39f37..8df26abce 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/01fcdfcf5/web/src/environment.ts#L86">environment.ts:86</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/environment.ts#L70">environment.ts:70</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/environment.ts#L69">environment.ts:69</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/environment.ts#L78">environment.ts:78</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/environment.ts#L84">environment.ts:84</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/environment.ts#L105">environment.ts:105</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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 a20f2d706..c7b832dfc 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/01fcdfcf5/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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 aca199fcb..49ad54e84 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/01fcdfcf5/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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 4ddc474ab..48f3b861a 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/01fcdfcf5/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -698,7 +698,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/01fcdfcf5/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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 7e04f8b65..e20a72b17 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/01fcdfcf5/web/src/memory.ts#L40">memory.ts:40</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/memory.ts#L32">memory.ts:32</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/memory.ts#L33">memory.ts:33</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/memory.ts#L154">memory.ts:154</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/memory.ts#L90">memory.ts:90</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/memory.ts#L97">memory.ts:97</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/memory.ts#L74">memory.ts:74</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/memory.ts#L81">memory.ts:81</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/memory.ts#L104">memory.ts:104</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/memory.ts#L132">memory.ts:132</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/memory.ts#L145">memory.ts:145</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/memory.ts#L60">memory.ts:60</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/memory.ts#L67">memory.ts:67</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/memory.ts#L53">memory.ts:53</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/memory.ts#L114">memory.ts:114</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/memory.ts#L124">memory.ts:124</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/memory.ts#L175">memory.ts:175</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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 a22d222c0..4ecad4a35 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/01fcdfcf5/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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 1759b607d..c199c4bb5 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/01fcdfcf5/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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 f63d4da38..1abdd6775 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/01fcdfcf5/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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 619f9c073..ff01ee8b4 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/01fcdfcf5/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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 19b827c8d..d2c65e5d5 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/01fcdfcf5/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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 a2860d957..e99ad2a18 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/01fcdfcf5/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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 2d1a4d0cd..5142e09b9 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/01fcdfcf5/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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 74123ca07..1c1baf419 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/01fcdfcf5/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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 71c43334b..0e996a8ab 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/01fcdfcf5/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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 4514214fc..c81ec894f 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/01fcdfcf5/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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 9809ac26a..354b5a8e9 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/01fcdfcf5/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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 eea5f5afe..39f57faab 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/01fcdfcf5/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/support.ts#L25">support.ts:25</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/support.ts#L39">support.ts:39</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/support.ts#L52">support.ts:52</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/compact.ts#L38">compact.ts:38</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/environment.ts#L32">environment.ts:32</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/compact.ts#L24">compact.ts:24</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -1508,7 +1508,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/01fcdfcf5/web/src/support.ts#L62">support.ts:62</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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 c3d4f6ded..476550853 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/01fcdfcf5/web/src/types.ts#L52">types.ts:52</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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 0aaa33e59..badad3386 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/01fcdfcf5/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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 933ce80a3..e72a152e2 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/01fcdfcf5/web/src/types.ts#L34">types.ts:34</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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/01fcdfcf5/web/src/types.ts#L39">types.ts:39</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bb00a15c2/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 2fdb1b3f1..5e91e8072 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 929c09f87..f91b0fafb 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>00:20.922</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:22.155</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>00:20.916</p></td>
+<td><p>00:22.148</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 4050c0826..7e0855794 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 22.65s!
+resnet18_v1 inference graph built in 23.99s!
 </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 b5cffecd1..8b7310b80 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:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
   DeprecationWarning,
-yolov3-tiny inference graph built in 15.83s!
+yolov3-tiny inference graph built in 16.49s!
 </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 85b8c055b..17fd3efec 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>01:32.264</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:36.542</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>00:49.379</p></td>
+<td><p>00:52.220</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>00:42.885</p></td>
+<td><p>00:44.322</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 d3d38961d..5d1b6d65a 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>00:03.261</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.265</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>00:02.861</p></td>
+<td><p>00:02.857</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>00:00.400</p></td>
+<td><p>00:00.408</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 c3ad7c6a5..e016a961e 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>00:00.721</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.741</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>00:00.388</p></td>
+<td><p>00:00.398</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>00:00.333</p></td>
+<td><p>00:00.343</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 5733ed84e..aa4a1ec13 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -565,7 +565,7 @@ 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: 93.111 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 93.482 ms
 </pre></div>
 </div>
 </div>
@@ -639,6 +639,7 @@ automatically optimize a matrix multiplication, without the need to specify a
 search template.  It ends a series of examples that starts from the Tensor
 Expression (TE) language that demonstrates how TVM can optimize computational
 operations.</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  5.729 seconds)</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-auto-scheduler-matmul-x86-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../_downloads/eac4389b114db015e95cb3cdf8b86b83/auto_scheduler_matmul_x86.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">auto_scheduler_matmul_x86.py</span></code></a></p>
diff --git a/docs/tutorial/autotvm_matmul_x86.html b/docs/tutorial/autotvm_matmul_x86.html
index 5ec4e1ab5..1d8164931 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -669,16 +669,16 @@ 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: 10.59/10.59     result: MeasureResult(costs=(0.0253470342,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5390493869781494, timestamp=1661453325.3026946)       [(&#39;tile_y&#39;, [-1, 1]), (&#39;tile_x&#39;, [-1, 256])],None,80
-No: 2   GFLOPS: 2.95/10.59      result: MeasureResult(costs=(0.09090695480000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6036720275878906, timestamp=1661453326.9196548)        [(&#39;tile_y&#39;, [-1, 4]), (&#39;tile_x&#39;, [-1, 8])],None,32
-No: 3   GFLOPS: 11.84/11.84     result: MeasureResult(costs=(0.0226681616,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.560218095779419, timestamp=1661453327.9701195)        [(&#39;tile_y&#39;, [-1, 64]), (&#39;tile_x&#39;, [-1, 32])],None,56
-No: 4   GFLOPS: 1.59/11.84      result: MeasureResult(costs=(0.1689274108,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.821287155151367, timestamp=1661453330.8371866)        [(&#39;tile_y&#39;, [-1, 1]), (&#39;tile_x&#39;, [-1, 4])],None,20
-No: 5   GFLOPS: 3.61/11.84      result: MeasureResult(costs=(0.07433205940000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3297615051269531, timestamp=1661453332.29576)  [(&#39;tile_y&#39;, [-1, 256]), (&#39;tile_x&#39;, [-1, 16])],None,48
-No: 6   GFLOPS: 1.53/11.84      result: MeasureResult(costs=(0.1760127394,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.936185121536255, timestamp=1661453335.8039503)        [(&#39;tile_y&#39;, [-1, 512]), (&#39;tile_x&#39;, [-1, 4])],None,29
-No: 7   GFLOPS: 0.82/11.84      result: MeasureResult(costs=(0.327365736,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.3547515869140625, timestamp=1661453341.7317622)        [(&#39;tile_y&#39;, [-1, 512]), (&#39;tile_x&#39;, [-1, 2])],None,19
-No: 8   GFLOPS: 9.89/11.84      result: MeasureResult(costs=(0.0271289766,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5759289264678955, timestamp=1661453342.3274128)       [(&#39;tile_y&#39;, [-1, 4]), (&#39;tile_x&#39;, [-1, 64])],None,62
-No: 9   GFLOPS: 1.61/11.84      result: MeasureResult(costs=(0.1666052774,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.781675338745117, timestamp=1661453345.2292595)        [(&#39;tile_y&#39;, [-1, 2]), (&#39;tile_x&#39;, [-1, 2])],None,11
-No: 10  GFLOPS: 2.53/11.84      result: MeasureResult(costs=(0.106263207,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8240606784820557, timestamp=1661453347.0911853)        [(&#39;tile_y&#39;, [-1, 4]), (&#39;tile_x&#39;, [-1, 4])],None,22
+No: 1   GFLOPS: 8.82/8.82       result: MeasureResult(costs=(0.030417669599999995,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.629288911819458, timestamp=1661452775.4720354)        [(&#39;tile_y&#39;, [-1, 1]), (&#39;tile_x&#39;, [-1, 256])],None,80
+No: 2   GFLOPS: 2.13/8.82       result: MeasureResult(costs=(0.12575622960000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1732444763183594, timestamp=1661452777.6570754)        [(&#39;tile_y&#39;, [-1, 4]), (&#39;tile_x&#39;, [-1, 8])],None,32
+No: 3   GFLOPS: 11.74/11.74     result: MeasureResult(costs=(0.0228570148,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5562417507171631, timestamp=1661452778.725979)        [(&#39;tile_y&#39;, [-1, 64]), (&#39;tile_x&#39;, [-1, 32])],None,56
+No: 4   GFLOPS: 1.85/11.74      result: MeasureResult(costs=(0.1448999166,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4421818256378174, timestamp=1661452781.751723)        [(&#39;tile_y&#39;, [-1, 1]), (&#39;tile_x&#39;, [-1, 4])],None,20
+No: 5   GFLOPS: 3.58/11.74      result: MeasureResult(costs=(0.07503549579999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3387136459350586, timestamp=1661452783.2224953)        [(&#39;tile_y&#39;, [-1, 256]), (&#39;tile_x&#39;, [-1, 16])],None,48
+No: 6   GFLOPS: 1.77/11.74      result: MeasureResult(costs=(0.1513502148,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5829274654388428, timestamp=1661452785.848455)        [(&#39;tile_y&#39;, [-1, 512]), (&#39;tile_x&#39;, [-1, 4])],None,29
+No: 7   GFLOPS: 0.88/11.74      result: MeasureResult(costs=(0.3066290516,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.025393486022949, timestamp=1661452791.4603856)        [(&#39;tile_y&#39;, [-1, 512]), (&#39;tile_x&#39;, [-1, 2])],None,19
+No: 8   GFLOPS: 10.03/11.74     result: MeasureResult(costs=(0.026774842599999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5797567367553711, timestamp=1661452792.0542002)       [(&#39;tile_y&#39;, [-1, 4]), (&#39;tile_x&#39;, [-1, 64])],None,62
+No: 9   GFLOPS: 1.75/11.74      result: MeasureResult(costs=(0.15379882279999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.563011884689331, timestamp=1661452794.736932)  [(&#39;tile_y&#39;, [-1, 2]), (&#39;tile_x&#39;, [-1, 2])],None,11
+No: 10  GFLOPS: 2.76/11.74      result: MeasureResult(costs=(0.0971874326,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6627240180969238, timestamp=1661452796.454875)        [(&#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 b0a46cd94..698d66354 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -551,7 +551,7 @@ 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;: 499.75286977000104, &#39;median&#39;: 499.7251776500036, &#39;std&#39;: 0.6332072523480163}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{&#39;mean&#39;: 496.1014442699969, &#39;median&#39;: 495.984946599998, &#39;std&#39;: 0.6595242498605052}
 </pre></div>
 </div>
 </div>
@@ -706,178 +706,178 @@ 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:   17.52/  17.52 GFLOPS | Progress: (4/20) | 5.89 s
-[Task  1/25]  Current/Best:    6.14/  17.52 GFLOPS | Progress: (8/20) | 9.48 s
-[Task  1/25]  Current/Best:   11.53/  22.73 GFLOPS | Progress: (12/20) | 11.96 s
-[Task  1/25]  Current/Best:   16.44/  22.73 GFLOPS | Progress: (16/20) | 13.65 s
-[Task  1/25]  Current/Best:   11.58/  23.78 GFLOPS | Progress: (20/20) | 15.41 s Done.
+[Task  1/25]  Current/Best:   17.44/  17.44 GFLOPS | Progress: (4/20) | 5.97 s
+[Task  1/25]  Current/Best:    6.15/  17.44 GFLOPS | Progress: (8/20) | 9.55 s
+[Task  1/25]  Current/Best:   11.49/  22.77 GFLOPS | Progress: (12/20) | 12.07 s
+[Task  1/25]  Current/Best:   16.51/  22.77 GFLOPS | Progress: (16/20) | 13.77 s
+[Task  1/25]  Current/Best:   11.50/  23.89 GFLOPS | Progress: (20/20) | 15.56 s Done.
 
 [Task  2/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  2/25]  Current/Best:   12.19/  13.19 GFLOPS | Progress: (4/20) | 3.82 s
-[Task  2/25]  Current/Best:   14.15/  17.89 GFLOPS | Progress: (8/20) | 5.12 s
-[Task  2/25]  Current/Best:   21.05/  21.05 GFLOPS | Progress: (12/20) | 6.45 s
-[Task  2/25]  Current/Best:   12.51/  21.05 GFLOPS | Progress: (16/20) | 7.73 s
-[Task  2/25]  Current/Best:   19.89/  21.05 GFLOPS | Progress: (20/20) | 9.36 s Done.
+[Task  2/25]  Current/Best:   12.14/  13.10 GFLOPS | Progress: (4/20) | 3.98 s
+[Task  2/25]  Current/Best:   14.14/  18.56 GFLOPS | Progress: (8/20) | 5.30 s
+[Task  2/25]  Current/Best:   20.81/  20.81 GFLOPS | Progress: (12/20) | 6.63 s
+[Task  2/25]  Current/Best:   12.22/  20.81 GFLOPS | Progress: (16/20) | 7.94 s
+[Task  2/25]  Current/Best:   20.28/  20.81 GFLOPS | Progress: (20/20) | 9.58 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/  10.80 GFLOPS | Progress: (4/20) | 5.89 s
-[Task  3/25]  Current/Best:   15.28/  16.72 GFLOPS | Progress: (8/20) | 7.84 s
-[Task  3/25]  Current/Best:   15.00/  16.72 GFLOPS | Progress: (12/20) | 9.55 s
-[Task  3/25]  Current/Best:    7.19/  23.73 GFLOPS | Progress: (16/20) | 11.47 s
-[Task  3/25]  Current/Best:   12.64/  23.73 GFLOPS | Progress: (20/20) | 16.04 s Done.
+[Task  3/25]  Current/Best:    1.63/  10.81 GFLOPS | Progress: (4/20) | 5.89 s
+[Task  3/25]  Current/Best:   15.26/  16.70 GFLOPS | Progress: (8/20) | 7.85 s
+[Task  3/25]  Current/Best:   14.96/  16.70 GFLOPS | Progress: (12/20) | 9.57 s
+[Task  3/25]  Current/Best:    7.15/  23.51 GFLOPS | Progress: (16/20) | 11.52 s
+[Task  3/25]  Current/Best:   12.52/  23.51 GFLOPS | Progress: (20/20) | 16.11 s Done.
 
 [Task  4/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  4/25]  Current/Best:    9.51/  19.82 GFLOPS | Progress: (4/20) | 2.41 s
-[Task  4/25]  Current/Best:    6.80/  19.82 GFLOPS | Progress: (8/20) | 7.16 s
-[Task  4/25]  Current/Best:   22.15/  22.15 GFLOPS | Progress: (12/20) | 12.17 s
-[Task  4/25]  Current/Best:   16.87/  22.15 GFLOPS | Progress: (16/20) | 14.58 s
-[Task  4/25]  Current/Best:   13.35/  22.15 GFLOPS | Progress: (20/20) | 16.65 s Done.
+[Task  4/25]  Current/Best:    9.39/  19.65 GFLOPS | Progress: (4/20) | 2.45 s
+[Task  4/25]  Current/Best:    6.82/  19.65 GFLOPS | Progress: (8/20) | 7.26 s
+[Task  4/25]  Current/Best:   21.15/  21.15 GFLOPS | Progress: (12/20) | 12.31 s
+[Task  4/25]  Current/Best:   16.99/  21.15 GFLOPS | Progress: (16/20) | 14.76 s
+[Task  4/25]  Current/Best:   13.42/  21.15 GFLOPS | Progress: (20/20) | 16.73 s Done.
 
 [Task  5/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  5/25]  Current/Best:    9.49/  10.17 GFLOPS | Progress: (4/20) | 2.61 s
-[Task  5/25]  Current/Best:   11.60/  12.86 GFLOPS | Progress: (8/20) | 4.69 s
-[Task  5/25]  Current/Best:   11.20/  18.05 GFLOPS | Progress: (12/20) | 7.94 s
-[Task  5/25]  Current/Best:   11.62/  22.50 GFLOPS | Progress: (16/20) | 9.40 s
-[Task  5/25]  Current/Best:   12.04/  22.50 GFLOPS | Progress: (20/20) | 11.31 s Done.
+[Task  5/25]  Current/Best:    9.80/  10.38 GFLOPS | Progress: (4/20) | 2.61 s
+[Task  5/25]  Current/Best:   11.85/  13.09 GFLOPS | Progress: (8/20) | 4.67 s
+[Task  5/25]  Current/Best:   11.02/  18.16 GFLOPS | Progress: (12/20) | 7.91 s
+[Task  5/25]  Current/Best:   11.92/  22.52 GFLOPS | Progress: (16/20) | 9.33 s
+[Task  5/25]  Current/Best:   12.01/  22.52 GFLOPS | Progress: (20/20) | 11.21 s Done.
 
 [Task  6/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  6/25]  Current/Best:   12.20/  20.80 GFLOPS | Progress: (4/20) | 4.14 s
-[Task  6/25]  Current/Best:   18.94/  20.80 GFLOPS | Progress: (8/20) | 5.92 s
-[Task  6/25]  Current/Best:   12.64/  20.80 GFLOPS | Progress: (12/20) | 7.89 s
-[Task  6/25]  Current/Best:   19.99/  20.80 GFLOPS | Progress: (16/20) | 10.17 s
-[Task  6/25]  Current/Best:    3.71/  20.80 GFLOPS | Progress: (20/20) | 12.68 s Done.
+[Task  6/25]  Current/Best:   12.29/  20.79 GFLOPS | Progress: (4/20) | 4.18 s
+[Task  6/25]  Current/Best:   18.98/  20.79 GFLOPS | Progress: (8/20) | 5.94 s
+[Task  6/25]  Current/Best:   13.26/  20.79 GFLOPS | Progress: (12/20) | 7.91 s
+[Task  6/25]  Current/Best:   19.79/  20.79 GFLOPS | Progress: (16/20) | 10.16 s
+[Task  6/25]  Current/Best:    3.75/  20.79 GFLOPS | Progress: (20/20) | 12.67 s Done.
 
 [Task  7/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  7/25]  Current/Best:   11.13/  12.95 GFLOPS | Progress: (4/20) | 3.59 s
-[Task  7/25]  Current/Best:   20.23/  21.16 GFLOPS | Progress: (8/20) | 5.11 s
-[Task  7/25]  Current/Best:   16.02/  21.16 GFLOPS | Progress: (12/20) | 7.04 s
-[Task  7/25]  Current/Best:   12.22/  21.16 GFLOPS | Progress: (16/20) | 9.09 s
-[Task  7/25]  Current/Best:    6.38/  21.75 GFLOPS | Progress: (20/20) | 11.55 s Done.
+[Task  7/25]  Current/Best:   11.13/  12.78 GFLOPS | Progress: (4/20) | 3.68 s
+[Task  7/25]  Current/Best:   20.11/  21.05 GFLOPS | Progress: (8/20) | 5.22 s
+[Task  7/25]  Current/Best:   13.20/  21.05 GFLOPS | Progress: (12/20) | 7.21 s
+[Task  7/25]  Current/Best:   12.27/  21.05 GFLOPS | Progress: (16/20) | 9.25 s
+[Task  7/25]  Current/Best:    6.32/  21.55 GFLOPS | Progress: (20/20) | 11.73 s Done.
 
 [Task  8/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  8/25]  Current/Best:    9.77/  13.95 GFLOPS | Progress: (4/20) | 2.95 s
-[Task  8/25]  Current/Best:    9.32/  13.95 GFLOPS | Progress: (8/20) | 8.16 s
-[Task  8/25]  Current/Best:   12.74/  13.95 GFLOPS | Progress: (12/20) | 14.67 s
-[Task  8/25]  Current/Best:   18.96/  18.96 GFLOPS | Progress: (16/20) | 16.78 s
-[Task  8/25]  Current/Best:   19.39/  19.39 GFLOPS | Progress: (20/20) | 24.01 s Done.
+[Task  8/25]  Current/Best:   10.12/  14.46 GFLOPS | Progress: (4/20) | 2.95 s
+[Task  8/25]  Current/Best:    9.61/  14.46 GFLOPS | Progress: (8/20) | 8.12 s
+[Task  8/25]  Current/Best:   12.68/  14.46 GFLOPS | Progress: (12/20) | 14.76 s
+[Task  8/25]  Current/Best:   18.96/  18.96 GFLOPS | Progress: (16/20) | 16.86 s
+[Task  8/25]  Current/Best:   20.30/  20.30 GFLOPS | Progress: (20/20) | 24.03 s Done.
 
 [Task  9/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  9/25]  Current/Best:   14.36/  15.71 GFLOPS | Progress: (4/20) | 11.96 s
-[Task  9/25]  Current/Best:   23.41/  23.41 GFLOPS | Progress: (8/20) | 13.78 s
-[Task  9/25]  Current/Best:    8.26/  23.41 GFLOPS | Progress: (12/20) | 16.36 s
-[Task  9/25]  Current/Best:   16.38/  23.41 GFLOPS | Progress: (16/20) | 19.26 s
-[Task  9/25]  Current/Best:    9.22/  23.41 GFLOPS | Progress: (20/20) | 27.89 s
+[Task  9/25]  Current/Best:   14.26/  15.73 GFLOPS | Progress: (4/20) | 11.99 s
+[Task  9/25]  Current/Best:   22.95/  22.95 GFLOPS | Progress: (8/20) | 13.80 s
+[Task  9/25]  Current/Best:    8.21/  22.95 GFLOPS | Progress: (12/20) | 16.38 s
+[Task  9/25]  Current/Best:   17.90/  22.95 GFLOPS | Progress: (16/20) | 19.28 s
+[Task  9/25]  Current/Best:    9.10/  22.95 GFLOPS | Progress: (20/20) | 28.16 s
 [Task 10/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25]  Current/Best:   18.23/  18.23 GFLOPS | Progress: (4/20) | 2.57 s
-[Task 10/25]  Current/Best:   15.52/  18.23 GFLOPS | Progress: (8/20) | 4.20 s
-[Task 10/25]  Current/Best:   12.21/  18.96 GFLOPS | Progress: (12/20) | 5.76 s
-[Task 10/25]  Current/Best:   19.10/  20.22 GFLOPS | Progress: (16/20) | 6.87 s
-[Task 10/25]  Current/Best:    8.90/  20.22 GFLOPS | Progress: (20/20) | 8.42 s Done.
+[Task 10/25]  Current/Best:   18.26/  18.26 GFLOPS | Progress: (4/20) | 2.59 s
+[Task 10/25]  Current/Best:   15.52/  18.26 GFLOPS | Progress: (8/20) | 4.27 s
+[Task 10/25]  Current/Best:   13.44/  19.23 GFLOPS | Progress: (12/20) | 5.83 s
+[Task 10/25]  Current/Best:   18.89/  20.29 GFLOPS | Progress: (16/20) | 6.95 s
+[Task 10/25]  Current/Best:    8.85/  20.29 GFLOPS | Progress: (20/20) | 8.49 s Done.
 
 [Task 11/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25]  Current/Best:   12.32/  18.13 GFLOPS | Progress: (4/20) | 3.43 s
-[Task 11/25]  Current/Best:   16.92/  18.13 GFLOPS | Progress: (8/20) | 6.26 s
-[Task 11/25]  Current/Best:   18.06/  18.13 GFLOPS | Progress: (12/20) | 8.32 s
-[Task 11/25]  Current/Best:   13.51/  20.98 GFLOPS | Progress: (16/20) | 11.28 s
-[Task 11/25]  Current/Best:   19.38/  21.50 GFLOPS | Progress: (20/20) | 13.39 s Done.
+[Task 11/25]  Current/Best:   12.09/  18.14 GFLOPS | Progress: (4/20) | 3.37 s
+[Task 11/25]  Current/Best:   15.00/  18.14 GFLOPS | Progress: (8/20) | 6.22 s
+[Task 11/25]  Current/Best:   18.19/  18.19 GFLOPS | Progress: (12/20) | 8.32 s
+[Task 11/25]  Current/Best:   13.49/  20.94 GFLOPS | Progress: (16/20) | 11.22 s
+[Task 11/25]  Current/Best:   19.44/  21.53 GFLOPS | Progress: (20/20) | 13.36 s Done.
 
 [Task 12/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25]  Current/Best:    7.79/  18.38 GFLOPS | Progress: (4/20) | 5.79 s
-[Task 12/25]  Current/Best:    5.27/  18.38 GFLOPS | Progress: (8/20) | 9.78 s
-[Task 12/25]  Current/Best:   18.63/  18.85 GFLOPS | Progress: (12/20) | 11.77 s
-[Task 12/25]  Current/Best:   15.29/  18.85 GFLOPS | Progress: (16/20) | 14.74 s
-[Task 12/25]  Current/Best:   15.22/  18.94 GFLOPS | Progress: (20/20) | 16.68 s Done.
+[Task 12/25]  Current/Best:    7.76/  17.97 GFLOPS | Progress: (4/20) | 5.88 s
+[Task 12/25]  Current/Best:    5.24/  17.97 GFLOPS | Progress: (8/20) | 9.86 s
+[Task 12/25]  Current/Best:   18.96/  19.02 GFLOPS | Progress: (12/20) | 11.88 s
+[Task 12/25]  Current/Best:   15.39/  19.02 GFLOPS | Progress: (16/20) | 14.83 s
+[Task 12/25]  Current/Best:   15.19/  19.02 GFLOPS | Progress: (20/20) | 16.76 s Done.
 
 [Task 13/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25]  Current/Best:    8.56/  17.41 GFLOPS | Progress: (4/20) | 3.83 s
-[Task 13/25]  Current/Best:   15.12/  20.93 GFLOPS | Progress: (8/20) | 6.47 s
-[Task 13/25]  Current/Best:   19.72/  21.59 GFLOPS | Progress: (12/20) | 9.51 s
-[Task 13/25]  Current/Best:   12.23/  21.59 GFLOPS | Progress: (16/20) | 13.00 s
-[Task 13/25]  Current/Best:   18.39/  21.59 GFLOPS | Progress: (20/20) | 15.35 s Done.
+[Task 13/25]  Current/Best:    8.43/  17.30 GFLOPS | Progress: (4/20) | 3.84 s
+[Task 13/25]  Current/Best:   15.16/  20.91 GFLOPS | Progress: (8/20) | 6.49 s
+[Task 13/25]  Current/Best:   19.57/  21.71 GFLOPS | Progress: (12/20) | 9.54 s
+[Task 13/25]  Current/Best:   12.25/  21.71 GFLOPS | Progress: (16/20) | 13.01 s
+[Task 13/25]  Current/Best:   18.70/  21.71 GFLOPS | Progress: (20/20) | 15.31 s Done.
 
 [Task 14/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25]  Current/Best:   13.56/  13.56 GFLOPS | Progress: (4/20) | 3.45 s
-[Task 14/25]  Current/Best:    6.08/  13.56 GFLOPS | Progress: (8/20) | 5.64 s
-[Task 14/25]  Current/Best:   20.24/  20.24 GFLOPS | Progress: (12/20) | 8.31 s
-[Task 14/25]  Current/Best:   16.70/  20.24 GFLOPS | Progress: (16/20) | 9.98 s Done.
+[Task 14/25]  Current/Best:   13.63/  13.63 GFLOPS | Progress: (4/20) | 3.39 s
+[Task 14/25]  Current/Best:    6.12/  13.63 GFLOPS | Progress: (8/20) | 5.57 s
+[Task 14/25]  Current/Best:   20.61/  20.61 GFLOPS | Progress: (12/20) | 8.27 s
+[Task 14/25]  Current/Best:   16.85/  20.61 GFLOPS | Progress: (16/20) | 9.95 s Done.
 
-[Task 14/25]  Current/Best:   17.37/  20.24 GFLOPS | Progress: (20/20) | 11.73 s
+[Task 14/25]  Current/Best:   17.18/  20.61 GFLOPS | Progress: (20/20) | 11.71 s
 [Task 15/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25]  Current/Best:   16.21/  17.63 GFLOPS | Progress: (4/20) | 2.73 s
-[Task 15/25]  Current/Best:   13.26/  18.08 GFLOPS | Progress: (8/20) | 4.07 s
-[Task 15/25]  Current/Best:   10.38/  22.34 GFLOPS | Progress: (12/20) | 6.36 s
-[Task 15/25]  Current/Best:   20.43/  22.34 GFLOPS | Progress: (16/20) | 9.41 s
-[Task 15/25]  Current/Best:    9.71/  22.34 GFLOPS | Progress: (20/20) | 10.42 s
+[Task 15/25]  Current/Best:   16.15/  17.64 GFLOPS | Progress: (4/20) | 2.76 s
+[Task 15/25]  Current/Best:   14.40/  18.03 GFLOPS | Progress: (8/20) | 4.09 s
+[Task 15/25]  Current/Best:   10.37/  22.25 GFLOPS | Progress: (12/20) | 6.37 s
+[Task 15/25]  Current/Best:   20.38/  22.25 GFLOPS | Progress: (16/20) | 9.63 s
+[Task 15/25]  Current/Best:    9.69/  22.25 GFLOPS | Progress: (20/20) | 10.65 s
 [Task 16/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25]  Current/Best:   20.31/  20.31 GFLOPS | Progress: (4/20) | 2.97 s
-[Task 16/25]  Current/Best:    2.97/  20.31 GFLOPS | Progress: (8/20) | 4.60 s
-[Task 16/25]  Current/Best:   19.15/  20.31 GFLOPS | Progress: (12/20) | 5.81 s
-[Task 16/25]  Current/Best:   17.72/  20.31 GFLOPS | Progress: (16/20) | 7.20 s
-[Task 16/25]  Current/Best:    9.95/  21.85 GFLOPS | Progress: (20/20) | 9.40 s Done.
+[Task 16/25]  Current/Best:   20.32/  20.32 GFLOPS | Progress: (4/20) | 3.04 s
+[Task 16/25]  Current/Best:    3.03/  20.32 GFLOPS | Progress: (8/20) | 4.67 s
+[Task 16/25]  Current/Best:   19.29/  20.32 GFLOPS | Progress: (12/20) | 5.90 s
+[Task 16/25]  Current/Best:   17.95/  20.32 GFLOPS | Progress: (16/20) | 7.31 s
+[Task 16/25]  Current/Best:   10.03/  21.93 GFLOPS | Progress: (20/20) | 9.48 s Done.
 
 [Task 17/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25]  Current/Best:   12.82/  16.77 GFLOPS | Progress: (4/20) | 4.85 s
-[Task 17/25]  Current/Best:   13.13/  23.24 GFLOPS | Progress: (8/20) | 7.74 s
-[Task 17/25]  Current/Best:   17.13/  23.24 GFLOPS | Progress: (12/20) | 9.80 s
-[Task 17/25]  Current/Best:   16.64/  23.24 GFLOPS | Progress: (16/20) | 12.06 s
-[Task 17/25]  Current/Best:   10.05/  23.24 GFLOPS | Progress: (20/20) | 14.21 s Done.
+[Task 17/25]  Current/Best:   13.26/  18.52 GFLOPS | Progress: (4/20) | 4.84 s
+[Task 17/25]  Current/Best:   13.79/  22.93 GFLOPS | Progress: (8/20) | 7.65 s
+[Task 17/25]  Current/Best:   17.78/  22.93 GFLOPS | Progress: (12/20) | 9.72 s
+[Task 17/25]  Current/Best:   16.36/  22.93 GFLOPS | Progress: (16/20) | 11.97 s
+[Task 17/25]  Current/Best:    9.94/  22.93 GFLOPS | Progress: (20/20) | 14.16 s Done.
 
 [Task 18/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25]  Current/Best:   11.37/  18.08 GFLOPS | Progress: (4/20) | 3.83 s
-[Task 18/25]  Current/Best:   10.55/  18.08 GFLOPS | Progress: (8/20) | 7.60 s
-[Task 18/25]  Current/Best:   18.99/  18.99 GFLOPS | Progress: (12/20) | 9.55 s
-[Task 18/25]  Current/Best:    9.99/  18.99 GFLOPS | Progress: (16/20) | 13.46 s
-[Task 18/25]  Current/Best:   20.55/  20.55 GFLOPS | Progress: (20/20) | 14.99 s Done.
+[Task 18/25]  Current/Best:   11.40/  17.48 GFLOPS | Progress: (4/20) | 3.87 s
+[Task 18/25]  Current/Best:   10.61/  20.00 GFLOPS | Progress: (8/20) | 7.59 s
+[Task 18/25]  Current/Best:   19.52/  20.00 GFLOPS | Progress: (12/20) | 9.51 s
+[Task 18/25]  Current/Best:    9.98/  20.00 GFLOPS | Progress: (16/20) | 13.41 s
+[Task 18/25]  Current/Best:   20.33/  20.33 GFLOPS | Progress: (20/20) | 14.93 s Done.
 
 [Task 19/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25]  Current/Best:    7.16/  20.45 GFLOPS | Progress: (4/20) | 6.18 s
-[Task 19/25]  Current/Best:    2.69/  20.45 GFLOPS | Progress: (8/20) | 9.50 s
-[Task 19/25]  Current/Best:   20.07/  20.45 GFLOPS | Progress: (12/20) | 12.56 s
-[Task 19/25]  Current/Best:   14.41/  21.45 GFLOPS | Progress: (16/20) | 15.60 s
-[Task 19/25]  Current/Best:    2.70/  22.84 GFLOPS | Progress: (20/20) | 18.39 s Done.
+[Task 19/25]  Current/Best:    6.80/  20.27 GFLOPS | Progress: (4/20) | 6.22 s
+[Task 19/25]  Current/Best:    2.69/  20.27 GFLOPS | Progress: (8/20) | 9.53 s
+[Task 19/25]  Current/Best:   19.79/  20.97 GFLOPS | Progress: (12/20) | 12.48 s
+[Task 19/25]  Current/Best:   14.53/  20.97 GFLOPS | Progress: (16/20) | 15.53 s
+[Task 19/25]  Current/Best:    2.70/  22.99 GFLOPS | Progress: (20/20) | 18.36 s Done.
 
 [Task 20/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25]  Current/Best:   10.23/  15.22 GFLOPS | Progress: (4/20) | 3.35 s Done.
+[Task 20/25]  Current/Best:    9.16/  15.12 GFLOPS | Progress: (4/20) | 3.41 s Done.
  Done.
 
-[Task 20/25]  Current/Best:   10.51/  15.22 GFLOPS | Progress: (8/20) | 6.87 s
-[Task 20/25]  Current/Best:    2.34/  16.71 GFLOPS | Progress: (12/20) | 10.80 s
-[Task 20/25]  Current/Best:   12.29/  16.71 GFLOPS | Progress: (16/20) | 14.79 s
-[Task 20/25]  Current/Best:   12.58/  21.88 GFLOPS | Progress: (20/20) | 16.89 s
+[Task 20/25]  Current/Best:   10.37/  15.12 GFLOPS | Progress: (8/20) | 6.83 s
+[Task 20/25]  Current/Best:    2.33/  16.59 GFLOPS | Progress: (12/20) | 10.72 s
+[Task 20/25]  Current/Best:   11.05/  16.59 GFLOPS | Progress: (16/20) | 14.53 s
+[Task 20/25]  Current/Best:   13.54/  21.81 GFLOPS | Progress: (20/20) | 16.63 s
 [Task 21/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25]  Current/Best:    6.42/  17.75 GFLOPS | Progress: (4/20) | 3.32 s
-[Task 21/25]  Current/Best:   14.49/  17.75 GFLOPS | Progress: (8/20) | 4.87 s
-[Task 21/25]  Current/Best:    1.61/  17.75 GFLOPS | Progress: (12/20) | 6.99 s
-[Task 21/25]  Current/Best:   17.29/  17.75 GFLOPS | Progress: (16/20) | 10.54 s
-[Task 21/25]  Current/Best:    4.47/  17.75 GFLOPS | Progress: (20/20) | 17.90 s
+[Task 21/25]  Current/Best:    6.39/  17.65 GFLOPS | Progress: (4/20) | 3.34 s
+[Task 21/25]  Current/Best:   14.52/  17.65 GFLOPS | Progress: (8/20) | 4.95 s
+[Task 21/25]  Current/Best:    1.61/  17.65 GFLOPS | Progress: (12/20) | 7.13 s
+[Task 21/25]  Current/Best:   17.98/  17.98 GFLOPS | Progress: (16/20) | 10.73 s
+[Task 21/25]  Current/Best:    4.45/  17.98 GFLOPS | Progress: (20/20) | 18.22 s
 [Task 22/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25]  Current/Best:    2.70/  16.97 GFLOPS | Progress: (4/20) | 2.70 s
-[Task 22/25]  Current/Best:    8.63/  21.99 GFLOPS | Progress: (8/20) | 4.74 s
-[Task 22/25]  Current/Best:   19.92/  21.99 GFLOPS | Progress: (12/20) | 7.13 s
-[Task 22/25]  Current/Best:   15.09/  21.99 GFLOPS | Progress: (16/20) | 9.27 s
-[Task 22/25]  Current/Best:   13.97/  21.99 GFLOPS | Progress: (20/20) | 10.95 s Done.
+[Task 22/25]  Current/Best:    2.70/  16.96 GFLOPS | Progress: (4/20) | 2.74 s
+[Task 22/25]  Current/Best:    9.15/  21.83 GFLOPS | Progress: (8/20) | 4.74 s
+[Task 22/25]  Current/Best:   19.81/  21.83 GFLOPS | Progress: (12/20) | 7.17 s
+[Task 22/25]  Current/Best:   15.34/  21.83 GFLOPS | Progress: (16/20) | 9.33 s
+[Task 22/25]  Current/Best:   14.91/  21.83 GFLOPS | Progress: (20/20) | 11.08 s Done.
 
 [Task 23/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25]  Current/Best:   17.72/  20.89 GFLOPS | Progress: (4/20) | 3.27 s
-[Task 23/25]  Current/Best:   14.33/  20.89 GFLOPS | Progress: (8/20) | 6.64 s
-[Task 23/25]  Current/Best:   21.02/  21.80 GFLOPS | Progress: (12/20) | 8.49 s
-[Task 23/25]  Current/Best:    6.41/  21.80 GFLOPS | Progress: (16/20) | 15.59 s
-[Task 23/25]  Current/Best:    7.96/  21.80 GFLOPS | Progress: (20/20) | 19.79 s Done.
+[Task 23/25]  Current/Best:   17.34/  20.28 GFLOPS | Progress: (4/20) | 3.30 s
+[Task 23/25]  Current/Best:   14.94/  20.28 GFLOPS | Progress: (8/20) | 6.71 s
+[Task 23/25]  Current/Best:   20.75/  21.24 GFLOPS | Progress: (12/20) | 8.58 s
+[Task 23/25]  Current/Best:    5.94/  21.24 GFLOPS | Progress: (16/20) | 15.83 s
+[Task 23/25]  Current/Best:    7.27/  21.24 GFLOPS | Progress: (20/20) | 20.13 s Done.
 
 [Task 24/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25]  Current/Best:    8.27/   8.27 GFLOPS | Progress: (4/20) | 11.83 s
-[Task 24/25]  Current/Best:    2.13/   8.27 GFLOPS | Progress: (8/20) | 22.90 s
-[Task 24/25]  Current/Best:    4.10/   8.27 GFLOPS | Progress: (12/20) | 34.43 s Done.
+[Task 24/25]  Current/Best:    8.66/   8.66 GFLOPS | Progress: (4/20) | 11.86 s
+[Task 24/25]  Current/Best:    2.12/   8.66 GFLOPS | Progress: (8/20) | 22.89 s
+[Task 24/25]  Current/Best:    4.26/   8.66 GFLOPS | Progress: (12/20) | 34.49 s Done.
 
-[Task 24/25]  Current/Best:    6.26/   8.74 GFLOPS | Progress: (16/20) | 40.14 s
-[Task 24/25]  Current/Best:    3.40/   8.74 GFLOPS | Progress: (20/20) | 46.19 s Done.
+[Task 24/25]  Current/Best:    6.75/   8.66 GFLOPS | Progress: (16/20) | 40.27 s
+[Task 24/25]  Current/Best:    3.30/   8.69 GFLOPS | Progress: (20/20) | 46.39 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/   2.88 GFLOPS | Progress: (4/20) | 11.59 s
-[Task 25/25]  Current/Best:    5.99/   8.24 GFLOPS | Progress: (8/20) | 22.90 s
-[Task 25/25]  Current/Best:    6.03/   8.24 GFLOPS | Progress: (12/20) | 34.40 s
-[Task 25/25]  Current/Best:    5.85/   8.77 GFLOPS | Progress: (16/20) | 36.15 s
-[Task 25/25]  Current/Best:    2.87/   9.26 GFLOPS | Progress: (20/20) | 46.82 s
+[Task 25/25]  Current/Best:    1.54/   2.88 GFLOPS | Progress: (4/20) | 11.64 s
+[Task 25/25]  Current/Best:    5.65/   7.89 GFLOPS | Progress: (8/20) | 22.96 s
+[Task 25/25]  Current/Best:    5.62/   7.89 GFLOPS | Progress: (12/20) | 34.47 s
+[Task 25/25]  Current/Best:    5.70/   9.22 GFLOPS | Progress: (16/20) | 36.45 s
+[Task 25/25]  Current/Best:    2.89/   9.22 GFLOPS | Progress: (20/20) | 47.13 s
 </pre></div>
 </div>
 <p>The output from this tuning process will look something like this:</p>
@@ -981,8 +981,8 @@ 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;: 407.3998885199967, &#39;median&#39;: 407.39381009999533, &#39;std&#39;: 0.6752243425527152}
-unoptimized: {&#39;mean&#39;: 499.75286977000104, &#39;median&#39;: 499.7251776500036, &#39;std&#39;: 0.6332072523480163}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {&#39;mean&#39;: 413.2848333200059, &#39;median&#39;: 413.1303025999955, &#39;std&#39;: 0.7787494950685662}
+unoptimized: {&#39;mean&#39;: 496.1014442699969, &#39;median&#39;: 495.984946599998, &#39;std&#39;: 0.6595242498605052}
 </pre></div>
 </div>
 </div>
@@ -996,7 +996,7 @@ 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  31.391 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes  34.685 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 ac6fab023..fd58c46a4 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -527,7 +527,7 @@ 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>1.283e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.272e-07 secs/op
 </pre></div>
 </div>
 </div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index 070d06d0c..b1a2a63fa 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -484,7 +484,7 @@ 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, 0x19a5c3f0)), stage(b, placeholder(b, 0x43f50f0)), 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, 0xbe94460)), stage(b, placeholder(b, 0x99bb6d0)), 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=[it [...]
 </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 99c4801c4..020435fa0 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>13:26.266</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>13:38.222</strong> total execution time for <strong>tutorial</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 83%" />
@@ -336,35 +336,35 @@
 </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>10:31.391</p></td>
+<td><p>10:34.685</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>01:00.956</p></td>
+<tr class="row-even"><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>01:05.729</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>00:55.627</p></td>
+<tr class="row-odd"><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>00:59.935</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>00:30.825</p></td>
+<td><p>00:31.247</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>00:25.269</p></td>
+<td><p>00:24.625</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <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>00:01.350</p></td>
+<td><p>00:01.131</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <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>00:00.698</p></td>
+<td><p>00:00.706</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>00:00.142</p></td>
+<td><p>00:00.156</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>
@@ -372,7 +372,7 @@
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="uma.html#sphx-glr-tutorial-uma-py"><span class="std std-ref">Making your Hardware Accelerator TVM-ready with UMA</span></a> (<code class="docutils literal notranslate"><span class="pre">uma.py</span></code>)</p></td>
-<td><p>00:00.002</p></td>
+<td><p>00:00.001</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="tvmc_command_line_driver.html#sphx-glr-tutorial-tvmc-command-line-driver-py"><span class="std std-ref">Compiling and Optimizing a Model with TVMC</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_command_line_driver.py</span></code>)</p></td>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index d6ba6506a..70ce5d231 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -542,8 +542,8 @@ 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: 0.000009
-naive: 0.000007
+<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>
@@ -635,7 +635,7 @@ 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:267: 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: 0.000026
+vector: 0.000025
 @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;),
@@ -668,10 +668,10 @@ vector: 0.000026
 </pre></div>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator                  Timing             Performance
-   numpy    8.653610000237678e-06                    1.0
-   naive              6.7228e-06      0.7768780890074031
-parallel              6.0385e-06      0.6978012644242285
-  vector    2.6289899999999997e-05    3.0380269042951933
+   numpy    7.0908500015320895e-06                   1.0
+   naive              5.8344e-06      0.8228068565460257
+parallel               6.161e-06       0.868866214723033
+  vector    2.4562899999999998e-05    3.4640275840968004
 </pre></div>
 </div>
 <div class="admonition-code-specialization admonition">
@@ -987,7 +987,7 @@ 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: 0.018314
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018526
 </pre></div>
 </div>
 <p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -1030,7 +1030,7 @@ 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:267: 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: 3.438344
+none: 3.307796
 </pre></div>
 </div>
 <p>Let’s take a look at the intermediate representation of the operator and
@@ -1097,7 +1097,7 @@ 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:267: 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: 0.286687
+blocking: 0.314472
 </pre></div>
 </div>
 <p>By reordering the computation to take advantage of caching, you should see a
@@ -1158,7 +1158,7 @@ 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:267: 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: 0.323368
+vectorization: 0.348802
 @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], []),
@@ -1215,7 +1215,7 @@ 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:267: 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: 0.117042
+loop permutation: 0.117619
 @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], []),
@@ -1293,7 +1293,7 @@ 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:267: 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: 0.110127
+array packing: 0.108992
 @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], []),
@@ -1369,7 +1369,7 @@ 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:267: 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: 0.110493
+block caching: 0.110536
 @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], []),
@@ -1438,7 +1438,7 @@ 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:267: 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: 0.146466
+parallelization: 0.146337
 @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], []),
@@ -1500,13 +1500,13 @@ 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      3.4383444901000004                     1.0
-        blocking     0.28668711139999997     0.08337940314749032
-   vectorization            0.3233684449     0.09404771564660619
-loop permutation     0.11704175829999999     0.03404014886728118
-   array packing     0.11012749070000001    0.032029219590151384
-   block caching            0.1104934692    0.032135659913700626
- parallelization     0.14646577460000001     0.04259776035290176
+            none            3.3077962892                     1.0
+        blocking            0.3144722179     0.09507000746290092
+   vectorization     0.34880158790000004     0.10544832795140438
+loop permutation     0.11761856560000002     0.03555798341754788
+   array packing     0.10899163969999999     0.03294992501680324
+   block caching     0.11053564180000001    0.033416701675644415
+ parallelization            0.1463374053     0.04424015039190703
 </pre></div>
 </div>
 <p>Note that the outputs on the web page reflect the running times on a
@@ -1538,7 +1538,6 @@ 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  0.956 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>