You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by tq...@apache.org on 2023/01/18 23:36:56 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@5d2a94720481ce2e065822229bcd4355c6e3945c)

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 45da671ae4 deploying docs (apache/tvm@5d2a94720481ce2e065822229bcd4355c6e3945c)
45da671ae4 is described below

commit 45da671ae41843f022cae81de6076b01e8e89bb9
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Wed Jan 18 23:36:50 2023 +0000

    deploying docs (apache/tvm@5d2a94720481ce2e065822229bcd4355c6e3945c)
---
 docs/_images/sphx_glr_micro_train_001.png          | Bin 332672 -> 324292 bytes
 docs/_images/sphx_glr_micro_train_thumb.png        | Bin 24174 -> 23851 bytes
 .../how_to/compile_models/from_darknet.rst.txt     |   2 +-
 .../how_to/compile_models/from_keras.rst.txt       |   2 +-
 .../how_to/compile_models/from_mxnet.rst.txt       |   2 +-
 .../how_to/compile_models/from_oneflow.rst.txt     |   2 +-
 .../how_to/compile_models/from_pytorch.rst.txt     |   2 +-
 .../how_to/compile_models/from_tensorflow.rst.txt  |   2 +-
 .../compile_models/sg_execution_times.rst.txt      |  22 +-
 .../deploy_models/deploy_model_on_adreno.rst.txt   |   2 +-
 .../deploy_models/deploy_model_on_android.rst.txt  |   2 +-
 .../deploy_object_detection_pytorch.rst.txt        |   4 +-
 .../deploy_models/deploy_prequantized.rst.txt      |   6 +-
 .../deploy_prequantized_tflite.rst.txt             |   4 +-
 .../how_to/deploy_models/deploy_quantized.rst.txt  |   2 +-
 .../deploy_models/deploy_ssd_gluoncv.rst.txt       |   4 +-
 .../deploy_models/sg_execution_times.rst.txt       |  20 +-
 .../extend_tvm/bring_your_own_datatypes.rst.txt    |   2 +-
 .../how_to/extend_tvm/sg_execution_times.rst.txt   |   8 +-
 .../how_to/extend_tvm/use_pass_instrument.rst.txt  |  16 +-
 .../optimize_operators/opt_conv_cuda.rst.txt       |   2 +-
 .../optimize_operators/opt_conv_tensorcore.rst.txt |   2 +-
 .../how_to/optimize_operators/opt_gemm.rst.txt     |  16 +-
 .../optimize_operators/sg_execution_times.rst.txt  |   8 +-
 .../sg_execution_times.rst.txt                     |  14 +-
 .../tune_conv2d_layer_cuda.rst.txt                 | 735 +++++++++++++++++++--
 .../tune_network_cuda.rst.txt                      |   4 +-
 .../tune_network_x86.rst.txt                       |   4 +-
 .../tune_sparse_x86.rst.txt                        |  20 +-
 .../tune_with_autotvm/sg_execution_times.rst.txt   |   8 +-
 .../tune_with_autotvm/tune_conv2d_cuda.rst.txt     | 241 +------
 .../work_with_microtvm/micro_autotune.rst.txt      |  16 +-
 .../work_with_microtvm/micro_pytorch.rst.txt       |   4 +-
 .../how_to/work_with_microtvm/micro_train.rst.txt  |  18 +-
 .../work_with_microtvm/sg_execution_times.rst.txt  |  12 +-
 .../work_with_relay/sg_execution_times.rst.txt     |   8 +-
 .../how_to/work_with_schedules/intrin_math.rst.txt |   2 +-
 .../work_with_schedules/sg_execution_times.rst.txt |  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     |   4 +-
 docs/_sources/tutorial/autotvm_matmul_x86.rst.txt  |  20 +-
 docs/_sources/tutorial/autotvm_relay_x86.rst.txt   |  57 +-
 .../tutorial/cross_compilation_and_rpc.rst.txt     |   2 +-
 docs/_sources/tutorial/intro_topi.rst.txt          |   2 +-
 docs/_sources/tutorial/sg_execution_times.rst.txt  |  22 +-
 .../tutorial/tensor_expr_get_started.rst.txt       |  42 +-
 docs/commit_hash                                   |   2 +-
 docs/how_to/compile_models/from_darknet.html       |   2 +-
 docs/how_to/compile_models/from_keras.html         |   2 +-
 docs/how_to/compile_models/from_mxnet.html         |   2 +-
 docs/how_to/compile_models/from_oneflow.html       |  13 +-
 docs/how_to/compile_models/from_pytorch.html       |   8 +-
 docs/how_to/compile_models/from_tensorflow.html    |   2 +-
 docs/how_to/compile_models/sg_execution_times.html |  26 +-
 .../deploy_models/deploy_model_on_adreno.html      |   2 +-
 .../deploy_models/deploy_model_on_android.html     |   2 +-
 .../deploy_object_detection_pytorch.html           |  40 +-
 docs/how_to/deploy_models/deploy_prequantized.html |   8 +-
 .../deploy_models/deploy_prequantized_tflite.html  |   4 +-
 docs/how_to/deploy_models/deploy_quantized.html    |   2 +-
 docs/how_to/deploy_models/deploy_ssd_gluoncv.html  |  36 +-
 docs/how_to/deploy_models/sg_execution_times.html  |  20 +-
 .../extend_tvm/bring_your_own_datatypes.html       |   2 +-
 docs/how_to/extend_tvm/sg_execution_times.html     |   8 +-
 docs/how_to/extend_tvm/use_pass_instrument.html    |  16 +-
 docs/how_to/optimize_operators/opt_conv_cuda.html  |   2 +-
 .../optimize_operators/opt_conv_tensorcore.html    |   2 +-
 docs/how_to/optimize_operators/opt_gemm.html       |  16 +-
 .../optimize_operators/sg_execution_times.html     |   8 +-
 .../sg_execution_times.html                        |  14 +-
 .../tune_conv2d_layer_cuda.html                    | 735 +++++++++++++++++++--
 .../tune_with_autoscheduler/tune_network_cuda.html |   4 +-
 .../tune_with_autoscheduler/tune_network_x86.html  |   4 +-
 .../tune_with_autoscheduler/tune_sparse_x86.html   |  20 +-
 .../tune_with_autotvm/sg_execution_times.html      |   8 +-
 .../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 241 +------
 docs/how_to/work_with_microtvm/micro_autotune.html |  16 +-
 docs/how_to/work_with_microtvm/micro_pytorch.html  |   5 +-
 docs/how_to/work_with_microtvm/micro_train.html    |  16 +-
 .../work_with_microtvm/sg_execution_times.html     |  12 +-
 .../how_to/work_with_relay/sg_execution_times.html |   8 +-
 docs/how_to/work_with_schedules/intrin_math.html   |   2 +-
 .../work_with_schedules/sg_execution_times.html    |  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       |   4 +-
 docs/tutorial/autotvm_matmul_x86.html              |  20 +-
 docs/tutorial/autotvm_relay_x86.html               | 275 ++++----
 docs/tutorial/cross_compilation_and_rpc.html       |   2 +-
 docs/tutorial/intro_topi.html                      |   2 +-
 docs/tutorial/sg_execution_times.html              |  26 +-
 docs/tutorial/tensor_expr_get_started.html         |  42 +-
 130 files changed, 2231 insertions(+), 1379 deletions(-)

diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index 3f59a37dab..fd04aec899 100644
Binary files a/docs/_images/sphx_glr_micro_train_001.png and b/docs/_images/sphx_glr_micro_train_001.png differ
diff --git a/docs/_images/sphx_glr_micro_train_thumb.png b/docs/_images/sphx_glr_micro_train_thumb.png
index 6746d44e45..176d23232e 100644
Binary files a/docs/_images/sphx_glr_micro_train_thumb.png and b/docs/_images/sphx_glr_micro_train_thumb.png differ
diff --git a/docs/_sources/how_to/compile_models/from_darknet.rst.txt b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
index c93c9e5f9e..833735b9e3 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -318,7 +318,7 @@ The process is no different from other examples.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  16.314 seconds)
+   **Total running time of the script:** ( 1 minutes  16.641 seconds)
 
 
 .. _sphx_glr_download_how_to_compile_models_from_darknet.py:
diff --git a/docs/_sources/how_to/compile_models/from_keras.rst.txt b/docs/_sources/how_to/compile_models/from_keras.rst.txt
index bd9874d4d7..8c83ccad4f 100644
--- a/docs/_sources/how_to/compile_models/from_keras.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_keras.rst.txt
@@ -232,7 +232,7 @@ Look up prediction top 1 index in 1000 class synset.
  .. code-block:: none
 
     Relay top-1 id: 285, class name: Egyptian cat
-
    1/1 [==============================] - ETA: 0s
    1/1 [==============================] - 1s 938ms/step
+
    1/1 [==============================] - ETA: 0s
    1/1 [==============================] - 1s 969ms/step
     Keras top-1 id: 285, class name: Egyptian cat
 
 
diff --git a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
index 6bc60988f0..659a7a38b4 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -116,7 +116,7 @@ In this section, we download a pretrained imagenet model and classify an image.
 
  .. code-block:: none
 
-    Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip97a8b984-afbf-4461-9c0f-bd955ea40d2d from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+    Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip731c29af-55b5-40e0-bdf4-c06c42a7a704 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 c862f3adf0..dd7848d36d 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -121,7 +121,7 @@ Load a pretrained OneFlow model and save model
  .. code-block:: none
 
     Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
      0%|          | 0.00/41.5M [00:00<?, ?B/s]
     19%|#9        | 7.99M/41.5M [00:00<00:00, 61.1MB/s]
     39%|###8      | 16.0M/41.5M [00:00<00:00, 63.5MB/s]
     58%|#####7    | 24.0M/41.5M [00:00<00:00, 55.1MB/s]
     77%|#######7  | 32.0M/41.5M [00:00<00:00, 54.4MB/s]
     96%|#########5| 39.7M/41.5M [00:00<00:00, 61.5MB/s]
    100%|##########| 41.5M/41.5M [00:00<00:00, 57.1MB/s]
+
      0%|          | 0.00/41.5M [00:00<?, ?B/s]
     15%|#5        | 6.33M/41.5M [00:00<00:01, 28.2MB/s]
     22%|##1       | 9.02M/41.5M [00:00<00:01, 27.3MB/s]
     39%|###8      | 16.0M/41.5M [00:00<00:00, 34.9MB/s]
     58%|#####7    | 24.0M/41.5M [00:00<00:00, 38.1MB/s]
     82%|########2 | 34.1M/41.5M [00:00<00:00, 53.4MB/s]
     96%|#########5| 39.7M/41.5M [00:00<00:00, 45.6MB/s]
    100%|##########| 41.5M/41.5M [00:01<00:00, 39.1MB/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 ed9ab42dcb..1acd084e47 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -101,7 +101,7 @@ Load a pretrained PyTorch model
     /venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=ResNet18_Weights.IMAGENET1K_V1`. You can also use `weights=ResNet18_Weights.DEFAULT` to get the most up-to-date weights.
       warnings.warn(msg)
     Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
-
      0%|          | 0.00/44.7M [00:00<?, ?B/s]
     24%|##3       | 10.6M/44.7M [00:00<00:00, 112MB/s]
     52%|#####2    | 23.3M/44.7M [00:00<00:00, 124MB/s]
     79%|#######8  | 35.1M/44.7M [00:00<00:00, 103MB/s]
    100%|##########| 44.7M/44.7M [00:00<00:00, 92.5MB/s]
+
      0%|          | 0.00/44.7M [00:00<?, ?B/s]
     18%|#7        | 7.99M/44.7M [00:00<00:00, 56.8MB/s]
     53%|#####3    | 23.7M/44.7M [00:00<00:00, 107MB/s] 
     77%|#######7  | 34.6M/44.7M [00:00<00:00, 99.4MB/s]
    100%|##########| 44.7M/44.7M [00:00<00:00, 98.6MB/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 06dce67fcf..567f12060a 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -424,7 +424,7 @@ Run the corresponding model on tensorflow
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  20.940 seconds)
+   **Total running time of the script:** ( 1 minutes  22.270 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 5d05515e08..7aa3756c72 100644
--- a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
 
 Computation times
 =================
-**06:20.263** total execution time for **how_to_compile_models** files:
+**06:23.600** total execution time for **how_to_compile_models** files:
 
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:20.940 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:22.270 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)       | 01:16.314 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)       | 01:16.641 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)         | 00:52.277 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)         | 00:53.033 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)       | 00:34.731 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)       | 00:35.979 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)           | 00:30.606 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)         | 00:30.512 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)         | 00:30.586 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)           | 00:30.511 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)         | 00:27.381 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)         | 00:26.788 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)       | 00:24.781 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)       | 00:24.518 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)           | 00:19.994 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)           | 00:20.686 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)             | 00:02.654 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)             | 00:02.662 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
index a4302de495..1e841f0735 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
@@ -727,7 +727,7 @@ well as provides information about the model's performance
     Evaluate inference time cost...
     Execution time summary:
      mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)  
-     2544.6756    2544.3626    2548.3481    2543.4752      1.3800   
+     2544.5067    2543.8345    2553.5584    2540.0831      3.7938   
                
 
 
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 d0a8bdeabd..2971e3edb7 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
@@ -437,7 +437,7 @@ Execute on TVM
     Evaluate inference time cost...
     Execution time summary:
      mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)  
-      16.7384      16.8832      17.2957      16.0486       0.4502   
+      16.4181      16.4232      17.2972      15.8568       0.4876   
                
 
 
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 3e4b75d84f..29eebd1704 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
@@ -130,7 +130,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
     /venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MaskRCNN_ResNet50_FPN_Weights.COCO_V1`. You can also use `weights=MaskRCNN_ResNet50_FPN_Weights.DEFAULT` to get the most up-to-date weights.
       warnings.warn(msg)
     Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
      0%|          | 0.00/170M [00:00<?, ?B/s]
      5%|4         | 7.99M/170M [00:00<00:02, 60.6MB/s]
     14%|#4        | 24.0M/170M [00:00<00:01, 99.4MB/s]
     20%|#9        | 33.6M/170M [00:00<00:01, 74.2MB/s]
     27%|##6       | 45.8M/170M [00:00<00:01, 90.0MB/s]
     33%|###2      | 56.0M/170M [00:00<00:01, 82.1MB/s]
     38%|###7      | 64.4M/170M [00:00<00:01, 67.4MB/s]
     44%|####3     | 74.1M/170M [00:01<00:01, 75.1MB/s]
     48%|####8     | 81.9M/170M [00:01<00:01, 75.6MB/s]
     54%|#####3    | 91.6M/170M [00:01<00:00, 82.3MB/s]
     61%|######1   | 104M/170M [00:01<00:00, 85.3MB/s] 
     66%|######6   | 112M/170M [00:01<00:00, 83.7MB/s]
     72%|#######1  | 122M/170M [00:01<00:00, 86.9MB/s]
     80%|########  | 136M/170M [00:01<00:00, 96.5MB/s]
     86%|########5 | 145M/170M [00:01<00:00, 95.3MB/s]
     91%|######### | 154M/170M [00:01<00:00, 81.6MB/s]
     96%|#########6| 163M/170M [00:02<00:00, 84.4MB/s]
    100%|##########| 170M/170M [00:02<00:00, 83.1MB/s]
+
      0%|          | 0.00/170M [00:00<?, ?B/s]
      5%|4         | 7.99M/170M [00:00<00:02, 66.9MB/s]
      9%|9         | 16.0M/170M [00:00<00:02, 74.6MB/s]
     14%|#4        | 24.0M/170M [00:00<00:02, 74.2MB/s]
     18%|#8        | 31.1M/170M [00:00<00:02, 70.0MB/s]
     22%|##2       | 37.8M/170M [00:00<00:02, 67.7MB/s]
     28%|##8       | 48.0M/170M [00:00<00:01, 68.7MB/s]
     33%|###2      | 56.0M/170M [00:00<00:01, 72.3MB/s]
     38%|###7      | 64.0M/170M [00:00<00:01, 71.0MB/s]
     42%|####2     | 72.0M/170M [00:01<00:01, 72.5MB/s]
     47%|####7     | 80.0M/170M [00:01<00:01, 60.4MB/s]
     53%|#####2    | 89.8M/170M [00:01<00:01, 70.6MB/s]
     58%|#####7    | 98.1M/170M [00:01<00:01, 74.8MB/s]
     62%|######2   | 106M/170M [00:01<00:00, 74.9MB/s] 
     68%|######8   | 116M/170M [00:01<00:00, 84.6MB/s]
     73%|#######3  | 125M/170M [00:01<00:00, 79.8MB/s]
     78%|#######7  | 132M/170M [00:01<00:00, 76.2MB/s]
     82%|########2 | 140M/170M [00:02<00:00, 68.1MB/s]
 
     86%|########6 | 147M/170M [00:02<00:00, 65.4MB/s]
     92%|#########1| 156M/170M [00:02<00:00, 73.3MB/s]
     98%|#########7| 166M/170M [00:02<00:00, 81.4MB/s]
    100%|##########| 170M/170M [00:02<00:00, 73.5MB/s]
     /venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
       for i in range(dim)
     /venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -299,7 +299,7 @@ Get boxes with score larger than 0.9
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 3 minutes  34.695 seconds)
+   **Total running time of the script:** ( 3 minutes  31.092 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 7ff228ae93..9033ce2196 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -227,7 +227,7 @@ training. Other models require a full post training calibration.
     /venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MobileNet_V2_Weights.IMAGENET1K_V1`. You can also use `weights=MobileNet_V2_Weights.DEFAULT` to get the most up-to-date weights.
       warnings.warn(msg)
     Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
      0%|          | 0.00/13.6M [00:00<?, ?B/s]
     59%|#####8    | 7.99M/13.6M [00:00<00:00, 55.3MB/s]
    100%|##########| 13.6M/13.6M [00:00<00:00, 79.7MB/s]
+
      0%|          | 0.00/13.6M [00:00<?, ?B/s]
     59%|#####8    | 7.99M/13.6M [00:00<00:00, 70.1MB/s]
    100%|##########| 13.6M/13.6M [00:00<00:00, 81.4MB/s]
 
 
 
@@ -409,7 +409,7 @@ 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)  
-      90.3247      90.2764      91.7873      90.1662       0.1911   
+      90.3536      90.3023      91.5031      90.1201       0.2210   
                
 
 
@@ -458,7 +458,7 @@ TODO
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  14.830 seconds)
+   **Total running time of the script:** ( 1 minutes  13.648 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 3c734e77b4..bb750130cd 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
@@ -423,7 +423,7 @@ Here we give an example of how to measure performance of TVM compiled models.
 
     Execution time summary:
      mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)  
-      120.1595     120.0529     126.2615     118.9527      0.7991   
+      121.1705     121.1662     123.4740     120.1414      0.5230   
                
 
 
@@ -460,7 +460,7 @@ 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  33.634 seconds)
+   **Total running time of the script:** ( 2 minutes  36.219 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 74b5b7a26e..549fe60a24 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -257,7 +257,7 @@ We create a Relay VM to build and execute the model.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  30.337 seconds)
+   **Total running time of the script:** ( 1 minutes  41.224 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 4b1f692c04..dc14331166 100644
--- a/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
@@ -170,7 +170,7 @@ Convert and compile model for CPU.
             data: None
       input_sym_arg_type = in_param.infer_type()[0]
     Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
      0%|          | 0/132723 [00:00<?, ?KB/s]
      5%|4         | 6533/132723 [00:00<00:01, 65323.37KB/s]
     11%|#1        | 15050/132723 [00:00<00:01, 76993.85KB/s]
     17%|#7        | 23021/132723 [00:00<00:01, 78228.80KB/s]
     24%|##3       | 31465/132723 [00:00<00:01, 80671.20KB/s]
     30%|###       | 39909/132723 [00:00<00:01, 82026.67KB/s]
     36%|###6      | 48321/132723 [00:00<00:01, 82734.67KB/s]
     43%|####2     | 56701/132723 [00:00<00:00, 83079.57KB/s]
     49%|####9     | 65140/132723 [00:00<00:00, 83494.90KB/s]
     56%|#####5    | 73750/132723 [00:00<00:00, 84306.36KB/s]
     62%|######2   | 82303/132723 [00:01<00:00, 84682.87KB/s]
     68%|######8   | 90772/132723 [00:01<00:00, 84670.56KB/s]
     75%|#######4  | 99312/132723 [00:01<00:00, 84890.79KB/s]
     81%|########1 | 107929/132723 [00:01<00:00, 85275.76KB/s]
     88%|########7 | 116517/132723 [00:01<00:00, 85454.83KB/s]
     94%|#########4| 125108/132723 [00:01<00:00, 85589.40KB/s]
    100%|########
 ##| 132723/132723 [00:01<00:00, 83416.58KB/s]
+
      0%|          | 0/132723 [00:00<?, ?KB/s]
      4%|4         | 5549/132723 [00:00<00:02, 55480.00KB/s]
     10%|#         | 13530/132723 [00:00<00:01, 69783.99KB/s]
     16%|#6        | 21504/132723 [00:00<00:01, 74325.52KB/s]
     22%|##2       | 29558/132723 [00:00<00:01, 76773.10KB/s]
     28%|##8       | 37599/132723 [00:00<00:01, 78083.21KB/s]
     34%|###4      | 45505/132723 [00:00<00:01, 78410.93KB/s]
     40%|####      | 53347/132723 [00:00<00:01, 78295.48KB/s]
     46%|####6     | 61177/132723 [00:00<00:00, 77924.61KB/s]
     52%|#####1    | 68970/132723 [00:00<00:00, 77763.46KB/s]
     58%|#####7    | 76747/132723 [00:01<00:00, 77761.05KB/s]
     64%|######3   | 84524/132723 [00:01<00:00, 77584.37KB/s]
     70%|######9   | 92283/132723 [00:01<00:00, 77531.59KB/s]
     75%|#######5  | 100037/132723 [00:01<00:00, 77315.25KB/s]
     81%|########1 | 107769/132723 [00:01<00:00, 77253.54KB/s]
     87%|########7 | 115496/132723 [00:01<00:00, 77251.20KB/s]
     93%|########
 #2| 123222/132723 [00:01<00:00, 77190.27KB/s]
     99%|#########8| 130984/132723 [00:01<00:00, 77315.01KB/s]
    100%|##########| 132723/132723 [00:01<00:00, 76846.23KB/s]
 
 
 
@@ -246,7 +246,7 @@ Display result
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 3 minutes  35.246 seconds)
+   **Total running time of the script:** ( 3 minutes  31.591 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 35623972b3..d7d76f4e61 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
 
 Computation times
 =================
-**14:59.337** total execution time for **how_to_deploy_models** files:
+**15:03.595** total execution time for **how_to_deploy_models** files:
 
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)                           | 03:35.246 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)                           | 03:31.591 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:34.695 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:31.092 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)           | 02:33.634 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)           | 02:36.219 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)                               | 01:30.337 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)                               | 01:41.224 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)                         | 01:14.830 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)                         | 01:13.648 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``)                   | 00:53.947 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``)                   | 00:53.778 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)                 | 00:41.053 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)                 | 00:40.505 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``)                       | 00:27.894 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``)                       | 00:27.912 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)                       | 00:27.696 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)                       | 00:27.620 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``)                                     | 00:00.006 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
index 258e622710..438bd76aeb 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
@@ -463,7 +463,7 @@ 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.zip52f2036a-8984-480b-83dd-d014682074bc from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+    Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip97a75cf9-e103-4d80-9a8b-55a928cdb2c5 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 86a60b35d8..c112457bb9 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
 =================
-**00:54.468** total execution time for **how_to_extend_tvm** files:
+**00:52.960** 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``) | 00:50.607 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:49.149 | 0.0 MB |
 +-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)           | 00:02.746 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)           | 00:02.714 | 0.0 MB |
 +-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)                     | 00:01.108 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)                     | 00:01.090 | 0.0 MB |
 +-------------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``)       | 00:00.007 | 0.0 MB |
 +-------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
index ee9251a6fb..92ac949fe4 100644
--- a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
@@ -220,10 +220,10 @@ profile the execution time of each passes.
  .. code-block:: none
 
     Printing results of timing profile...
-    InferType: 18360us [18360us] (48.36%; 48.36%)
-    FoldScaleAxis: 19607us [10us] (51.64%; 51.64%)
-            FoldConstant: 19597us [1711us] (51.62%; 99.95%)
-                    InferType: 17886us [17886us] (47.11%; 91.27%)
+    InferType: 18184us [18184us] (48.43%; 48.43%)
+    FoldScaleAxis: 19362us [8us] (51.57%; 51.57%)
+            FoldConstant: 19354us [1790us] (51.55%; 99.96%)
+                    InferType: 17564us [17564us] (46.78%; 90.75%)
 
 
 
@@ -262,10 +262,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
  .. code-block:: none
 
     Printing results of timing profile...
-    InferType: 17882us [17882us] (48.27%; 48.27%)
-    FoldScaleAxis: 19168us [7us] (51.73%; 51.73%)
-            FoldConstant: 19161us [1728us] (51.72%; 99.96%)
-                    InferType: 17433us [17433us] (47.05%; 90.98%)
+    InferType: 17828us [17828us] (47.89%; 47.89%)
+    FoldScaleAxis: 19403us [7us] (52.11%; 52.11%)
+            FoldConstant: 19396us [1734us] (52.10%; 99.96%)
+                    InferType: 17662us [17662us] (47.44%; 91.06%)
 
 
 
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 5861bbd4e0..6737dd61db 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
@@ -331,7 +331,7 @@ latency of convolution.
 
  .. code-block:: none
 
-    Convolution: 36.574817 ms
+    Convolution: 35.153598 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 d76ec25096..8171529512 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
@@ -608,7 +608,7 @@ be able to run on our build server
 
  .. code-block:: none
 
-    conv2d with tensor core: 13.187625 ms
+    conv2d with tensor core: 11.614768 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 3aa11dbb78..86e7eb930e 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -134,8 +134,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
 
  .. code-block:: none
 
-    Numpy running time: 0.019611
-    Baseline: 3.458809
+    Numpy running time: 0.019183
+    Baseline: 3.476481
 
 
 
@@ -227,7 +227,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
 
  .. code-block:: none
 
-    Opt1: 0.327382
+    Opt1: 0.314903
 
 
 
@@ -318,7 +318,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
 
  .. code-block:: none
 
-    Opt2: 0.346190
+    Opt2: 0.346718
 
 
 
@@ -406,7 +406,7 @@ the access pattern for A matrix is more cache friendly.
 
  .. code-block:: none
 
-    Opt3: 0.131481
+    Opt3: 0.122469
 
 
 
@@ -523,7 +523,7 @@ flattening.
 
  .. code-block:: none
 
-    Opt4: 0.110400
+    Opt4: 0.109833
 
 
 
@@ -635,7 +635,7 @@ write to C when all the block results are ready.
 
  .. code-block:: none
 
-    Opt5: 0.113464
+    Opt5: 0.111797
 
 
 
@@ -748,7 +748,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
 
  .. code-block:: none
 
-    Opt6: 0.148611
+    Opt6: 0.147873
 
 
 
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 53beccd204..b6a5a11b4f 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
 =================
-**00:36.018** total execution time for **how_to_optimize_operators** files:
+**00:35.639** total execution time for **how_to_optimize_operators** files:
 
 +-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)                       | 00:33.366 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)                       | 00:33.027 | 0.0 MB |
 +-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.535 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.539 | 0.0 MB |
 +-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)             | 00:01.117 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)             | 00:01.073 | 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 64b8064c47..f54620e38e 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
 
 Computation times
 =================
-**09:19.252** total execution time for **how_to_tune_with_autoscheduler** files:
+**09:15.990** total execution time for **how_to_tune_with_autoscheduler** files:
 
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:35.577 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:36.234 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)             | 01:40.746 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)             | 01:39.092 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)           | 01:06.985 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)           | 01:06.080 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)               | 00:28.559 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)               | 00:27.820 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)             | 00:14.183 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)             | 00:13.907 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)           | 00:13.202 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)           | 00:12.857 | 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 265281bd45..d83cff32db 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
@@ -245,12 +245,12 @@ cooperative fetching, unrolling and operator fusion.
             bias_1 = T.match_buffer(bias, (1, 512, 1, 1))
             compute_1 = T.match_buffer(compute, (1, 512, 7, 7))
             blockIdx_x = T.env_thread("blockIdx.x")
-            T.launch_thread(blockIdx_x, 64)
+            T.launch_thread(blockIdx_x, 32)
             conv2d_nchw = T.allocate([8], "float32", "local")
             pad_temp_shared = T.allocate([252], "float32", "shared")
-            kernel_shared = T.allocate([96], "float32", "shared")
+            kernel_shared = T.allocate([192], "float32", "shared")
             threadIdx_x = T.env_thread("threadIdx.x")
-            T.launch_thread(threadIdx_x, 49)
+            T.launch_thread(threadIdx_x, 98)
             conv2d_nchw_1 = T.buffer_decl((8,), data=conv2d_nchw, scope="local", align=32)
             conv2d_nchw_1[0] = T.float32(0)
             conv2d_nchw_1[1] = T.float32(0)
@@ -260,42 +260,342 @@ cooperative fetching, unrolling and operator fusion.
             conv2d_nchw_1[5] = T.float32(0)
             conv2d_nchw_1[6] = T.float32(0)
             conv2d_nchw_1[7] = T.float32(0)
-            for rc_outer_outer, rx_outer_outer in T.grid(128, 3):
+            for rc_outer_outer in range(128):
                 cse_var_1: T.int32 = rc_outer_outer * 196
                 threadIdx_x_1 = T.env_thread("threadIdx.x")
                 pad_temp_shared_1 = T.buffer_decl((252,), data=pad_temp_shared, scope="shared")
                 data_2 = T.buffer_decl((25088,), data=data_1.data)
-                with T.launch_thread(threadIdx_x_1, 49):
-                    pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(7 <= threadIdx_x_1 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_2[cse_var_1 + threadIdx_x_1 + rx_outer_outer - 8], T.float32(0))
-                with T.launch_thread(threadIdx_x_1, 49):
-                    pad_temp_shared_1[threadIdx_x_1 + 49] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 7) % 9 and (threadIdx_x_1 // 7 + 7) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_2[cse_var_1 + (threadIdx_x_1 + 49) // 63 * 49 + (threadIdx_x_1 // 7 + 7) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
-                with T.launch_thread(threadIdx_x_1, 49):
-                    pad_temp_shared_1[threadIdx_x_1 + 98] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 5) % 9 and (threadIdx_x_1 // 7 + 5) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_2[cse_var_1 + (threadIdx_x_1 + 98) // 63 * 49 + (threadIdx_x_1 // 7 + 5) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
-                with T.launch_thread(threadIdx_x_1, 49):
-                    pad_temp_shared_1[threadIdx_x_1 + 147] = T.if_then_else(1 <= (threadIdx_x_1 // 7 + 3) % 9 and (threadIdx_x_1 // 7 + 3) % 9 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_2[cse_var_1 + (threadIdx_x_1 + 147) // 63 * 49 + (threadIdx_x_1 // 7 + 3) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
-                with T.launch_thread(threadIdx_x_1, 49):
-                    pad_temp_shared_1[threadIdx_x_1 + 196] = T.if_then_else(1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_2[cse_var_1 + (threadIdx_x_1 + 196) // 63 * 49 + (threadIdx_x_1 // 7 + 1) * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
-                with T.launch_thread(threadIdx_x_1, 49):
-                    if T.likely(threadIdx_x_1 < 7):
-                        pad_temp_shared_1[threadIdx_x_1 + 245] = T.float32(0)
+                with T.launch_thread(threadIdx_x_1, 98):
+                    pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(9 <= threadIdx_x_1 % 63 and 1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_2[cse_var_1 + threadIdx_x_1 // 9 * 7 + threadIdx_x_1 % 9 - 8], T.float32(0))
+                with T.launch_thread(threadIdx_x_1, 98):
+                    pad_temp_shared_1[threadIdx_x_1 + 98] = T.if_then_else(9 <= (threadIdx_x_1 + 35) % 63 and 1 <= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 < 8, data_2[cse_var_1 + (threadIdx_x_1 + 98) // 9 * 7 + (threadIdx_x_1 + 8) % 9 - 8], T.float32(0))
+                with T.launch_thread(threadIdx_x_1, 98):
+                    if T.likely(threadIdx_x_1 < 56):
+                        pad_temp_shared_1[threadIdx_x_1 + 196] = T.if_then_else(9 <= (threadIdx_x_1 + 7) % 63 and 1 <= (threadIdx_x_1 + 7) % 9 and (threadIdx_x_1 + 7) % 9 < 8, data_2[cse_var_1 + (threadIdx_x_1 + 196) // 9 * 7 + (threadIdx_x_1 + 7) % 9 - 8], T.float32(0))
                 threadIdx_x_2 = T.env_thread("threadIdx.x")
-                kernel_shared_1 = T.buffer_decl((96,), data=kernel_shared, scope="shared")
+                kernel_shared_1 = T.buffer_decl((192,), data=kernel_shared, scope="shared")
                 kernel_2 = T.buffer_decl((2359296,), data=kernel_1.data)
-                with T.launch_thread(threadIdx_x_2, 49):
-                    kernel_shared_1[threadIdx_x_2] = kernel_2[blockIdx_x * 36864 + threadIdx_x_2 // 12 * 4608 + rc_outer_outer * 36 + threadIdx_x_2 % 12 * 3 + rx_outer_outer]
-                with T.launch_thread(threadIdx_x_2, 49):
-                    if T.likely(threadIdx_x_2 < 47):
-                        kernel_shared_1[threadIdx_x_2 + 49] = kernel_2[blockIdx_x * 36864 + (threadIdx_x_2 + 49) // 12 * 4608 + rc_outer_outer * 36 + (threadIdx_x_2 + 1) % 12 * 3 + rx_outer_outer]
-                for ry_outer_inner, ff_outer_inner in T.grid(3, 8):
-                    cse_var_2: T.int32 = ff_outer_inner * 12 + ry_outer_inner
-                    conv2d_nchw_1[ff_outer_inner] = conv2d_nchw_1[ff_outer_inner] + pad_temp_shared_1[ry_outer_inner * 7 + threadIdx_x] * kernel_shared_1[cse_var_2]
-                    conv2d_nchw_1[ff_outer_inner] = conv2d_nchw_1[ff_outer_inner] + pad_temp_shared_1[ry_outer_inner * 7 + threadIdx_x + 63] * kernel_shared_1[cse_var_2 + 3]
-                    conv2d_nchw_1[ff_outer_inner] = conv2d_nchw_1[ff_outer_inner] + pad_temp_shared_1[ry_outer_inner * 7 + threadIdx_x + 126] * kernel_shared_1[cse_var_2 + 6]
-                    conv2d_nchw_1[ff_outer_inner] = conv2d_nchw_1[ff_outer_inner] + pad_temp_shared_1[ry_outer_inner * 7 + threadIdx_x + 189] * kernel_shared_1[cse_var_2 + 9]
+                with T.launch_thread(threadIdx_x_2, 98):
+                    kernel_shared_1[threadIdx_x_2] = kernel_2[blockIdx_x * 73728 + threadIdx_x_2 // 12 * 4608 + rc_outer_outer * 36 + threadIdx_x_2 % 12 // 3 * 9 + threadIdx_x_2 % 3]
+                with T.launch_thread(threadIdx_x_2, 98):
+                    if T.likely(threadIdx_x_2 < 94):
+                        kernel_shared_1[threadIdx_x_2 + 98] = kernel_2[blockIdx_x * 73728 + (threadIdx_x_2 + 98) // 12 * 4608 + rc_outer_outer * 36 + (threadIdx_x_2 + 2) % 12 // 3 * 9 + (threadIdx_x_2 + 2) % 3]
+                conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96]
+                conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96 + 12]
+                conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 1]
+                conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 13]
+                conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 2]
+                conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 14]
+                conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96 + 24]
+                conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96 + 36]
+                conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 25]
+                conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 37]
+                conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 26]
+                conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 38]
+                conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96 + 48]
+                conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96 + 60]
+                conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 49]
+                conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 61]
+                conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 50]
+                conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 62]
+                conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96 + 72]
+                conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96 + 84]
+                conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 73]
+                conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 85]
+                conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 74]
+                conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 86]
+                conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 3]
+                conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 15]
+                conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 4]
+                conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 16]
+                conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 5]
+                conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 17]
+                conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 27]
+                conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 39]
+                conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 28]
+                conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 40]
+                conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 29]
+                conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 41]
+                conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 51]
+                conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 63]
+                conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 52]
+                conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 64]
+                conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 53]
+                conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 65]
+                conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 75]
+                conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 87]
+                conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 76]
+                conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 88]
+                conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 77]
+                conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 89]
+                conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 6]
+                conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 18]
+                conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 7]
+                conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 19]
+                conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 8]
+                conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 20]
+                conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 30]
+                conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 42]
+                conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 31]
+                conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 43]
+                conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 32]
+                conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 44]
+                conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 54]
+                conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 66]
+                conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 55]
+                conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 67]
+                conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 56]
+                conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 68]
+                conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 78]
+                conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 90]
+                conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 79]
+                conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 91]
+                conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 80]
+                conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 92]
+                conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 9]
+                conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 21]
+                conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 10]
+                conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 22]
+                conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 11]
+                conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 23]
+                conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 33]
+                conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 45]
+                conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 34]
+                conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 46]
+                conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 35]
+                conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 47]
+                conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 57]
+                conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 69]
+                conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 58]
+                conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 70]
+                conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 59]
+                conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 71]
+                conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 81]
+                conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 93]
+                conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 82]
+                conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 94]
+                conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 83]
+                conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 95]
+                with T.launch_thread(threadIdx_x_1, 98):
+                    pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_2[cse_var_1 + threadIdx_x_1 // 9 * 7 + threadIdx_x_1 % 9 - 1], T.float32(0))
+                with T.launch_thread(threadIdx_x_1, 98):
+                    pad_temp_shared_1[threadIdx_x_1 + 98] = T.if_then_else(1 <= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 < 8, data_2[cse_var_1 + (threadIdx_x_1 + 98) // 9 * 7 + (threadIdx_x_1 + 8) % 9 - 1], T.float32(0))
+                with T.launch_thread(threadIdx_x_1, 98):
+                    if T.likely(threadIdx_x_1 < 56):
+                        pad_temp_shared_1[threadIdx_x_1 + 196] = T.if_then_else(1 <= (threadIdx_x_1 + 7) % 9 and (threadIdx_x_1 + 7) % 9 < 8, data_2[cse_var_1 + (threadIdx_x_1 + 196) // 9 * 7 + (threadIdx_x_1 + 7) % 9 - 1], T.float32(0))
+                with T.launch_thread(threadIdx_x_2, 98):
+                    kernel_shared_1[threadIdx_x_2] = kernel_2[blockIdx_x * 73728 + threadIdx_x_2 // 12 * 4608 + rc_outer_outer * 36 + threadIdx_x_2 % 12 // 3 * 9 + threadIdx_x_2 % 3 + 3]
+                with T.launch_thread(threadIdx_x_2, 98):
+                    if T.likely(threadIdx_x_2 < 94):
+                        kernel_shared_1[threadIdx_x_2 + 98] = kernel_2[blockIdx_x * 73728 + (threadIdx_x_2 + 98) // 12 * 4608 + rc_outer_outer * 36 + (threadIdx_x_2 + 2) % 12 // 3 * 9 + (threadIdx_x_2 + 2) % 3 + 3]
+                conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96]
+                conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96 + 12]
+                conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 1]
+                conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 13]
+                conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 2]
+                conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 14]
+                conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96 + 24]
+                conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96 + 36]
+                conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 25]
+                conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 37]
+                conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 26]
+                conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 38]
+                conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96 + 48]
+                conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96 + 60]
+                conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 49]
+                conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 61]
+                conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 50]
+                conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 62]
+                conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96 + 72]
+                conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96 + 84]
+                conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 73]
+                conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 85]
+                conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 74]
+                conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 86]
+                conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 3]
+                conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 15]
+                conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 4]
+                conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 16]
+                conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 5]
+                conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 17]
+                conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 27]
+                conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 39]
+                conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 28]
+                conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 40]
+                conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 29]
+                conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 41]
+                conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 51]
+                conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 63]
+                conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 52]
+                conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 64]
+                conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 53]
+                conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 65]
+                conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 75]
+                conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 87]
+                conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 76]
+                conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 88]
+                conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 77]
+                conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 89]
+                conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 6]
+                conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 18]
+                conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 7]
+                conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 19]
+                conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 8]
+                conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 20]
+                conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 30]
+                conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 42]
+                conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 31]
+                conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 43]
+                conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 32]
+                conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 44]
+                conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 54]
+                conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 66]
+                conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 55]
+                conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 67]
+                conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 56]
+                conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 68]
+                conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 78]
+                conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 90]
+                conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 79]
+                conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 91]
+                conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 80]
+                conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 92]
+                conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 9]
+                conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 21]
+                conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 10]
+                conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 22]
+                conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 11]
+                conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 23]
+                conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 33]
+                conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 45]
+                conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 34]
+                conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 46]
+                conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 35]
+                conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 47]
+                conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 57]
+                conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 69]
+                conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 58]
+                conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 70]
+                conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 59]
+                conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 71]
+                conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 81]
+                conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 93]
+                conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 82]
+                conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 94]
+                conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 83]
+                conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 95]
+                with T.launch_thread(threadIdx_x_1, 98):
+                    pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(threadIdx_x_1 % 63 < 54 and 1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_2[cse_var_1 + threadIdx_x_1 // 9 * 7 + threadIdx_x_1 % 9 + 6], T.float32(0))
+                with T.launch_thread(threadIdx_x_1, 98):
+                    pad_temp_shared_1[threadIdx_x_1 + 98] = T.if_then_else((threadIdx_x_1 + 35) % 63 < 54 and 1 <= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 < 8, data_2[cse_var_1 + (threadIdx_x_1 + 98) // 9 * 7 + (threadIdx_x_1 + 8) % 9 + 6], T.float32(0))
+                with T.launch_thread(threadIdx_x_1, 98):
+                    if T.likely(threadIdx_x_1 < 56):
+                        pad_temp_shared_1[threadIdx_x_1 + 196] = T.if_then_else((threadIdx_x_1 + 7) % 63 < 54 and 1 <= (threadIdx_x_1 + 7) % 9 and (threadIdx_x_1 + 7) % 9 < 8, data_2[cse_var_1 + (threadIdx_x_1 + 196) // 9 * 7 + (threadIdx_x_1 + 7) % 9 + 6], T.float32(0))
+                with T.launch_thread(threadIdx_x_2, 98):
+                    kernel_shared_1[threadIdx_x_2] = kernel_2[blockIdx_x * 73728 + threadIdx_x_2 // 12 * 4608 + rc_outer_outer * 36 + threadIdx_x_2 % 12 // 3 * 9 + threadIdx_x_2 % 3 + 6]
+                with T.launch_thread(threadIdx_x_2, 98):
+                    if T.likely(threadIdx_x_2 < 94):
+                        kernel_shared_1[threadIdx_x_2 + 98] = kernel_2[blockIdx_x * 73728 + (threadIdx_x_2 + 98) // 12 * 4608 + rc_outer_outer * 36 + (threadIdx_x_2 + 2) % 12 // 3 * 9 + (threadIdx_x_2 + 2) % 3 + 6]
+                conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96]
+                conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96 + 12]
+                conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 1]
+                conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 13]
+                conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 2]
+                conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 14]
+                conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96 + 24]
+                conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96 + 36]
+                conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 25]
+                conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 37]
+                conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 26]
+                conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 38]
+                conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96 + 48]
+                conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96 + 60]
+                conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 49]
+                conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 61]
+                conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 50]
+                conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 62]
+                conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96 + 72]
+                conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96 + 84]
+                conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 73]
+                conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 85]
+                conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 74]
+                conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 86]
+                conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 3]
+                conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 15]
+                conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 4]
+                conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 16]
+                conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 5]
+                conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 17]
+                conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 27]
+                conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 39]
+                conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 28]
+                conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 40]
+                conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 29]
+                conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 41]
+                conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 51]
+                conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 63]
+                conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 52]
+                conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 64]
+                conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 53]
+                conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 65]
+                conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 75]
+                conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 87]
+                conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 76]
+                conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 88]
+                conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 77]
+                conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 89]
+                conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 6]
+                conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 18]
+                conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 7]
+                conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 19]
+                conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 8]
+                conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 20]
+                conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 30]
+                conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 42]
+                conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 31]
+                conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 43]
+                conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 32]
+                conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 44]
+                conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 54]
+                conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 66]
+                conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 55]
+                conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 67]
+                conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 56]
+                conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 68]
+                conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 78]
+                conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 90]
+                conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 79]
+                conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 91]
+                conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 80]
+                conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 92]
+                conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 9]
+                conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 21]
+                conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 10]
+                conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 22]
+                conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 11]
+                conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 23]
+                conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 33]
+                conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 45]
+                conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 34]
+                conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 46]
+                conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 35]
+                conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 47]
+                conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 57]
+                conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 69]
+                conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 58]
+                conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 70]
+                conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 59]
+                conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 71]
+                conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 81]
+                conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 93]
+                conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 82]
+                conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 94]
+                conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 83]
+                conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 95]
             for i1_inner in range(8):
                 compute_2 = T.buffer_decl((25088,), data=compute_1.data)
                 bias_2 = T.buffer_decl((512,), data=bias_1.data)
-                compute_2[blockIdx_x * 392 + i1_inner * 49 + threadIdx_x] = T.max(conv2d_nchw_1[i1_inner] + bias_2[blockIdx_x * 8 + i1_inner], T.float32(0))
+                compute_2[blockIdx_x * 784 + threadIdx_x // 49 * 392 + i1_inner * 49 + threadIdx_x % 49] = T.max(conv2d_nchw_1[i1_inner] + bias_2[blockIdx_x * 16 + threadIdx_x // 49 * 8 + i1_inner], T.float32(0))
 
 
 
@@ -345,7 +645,7 @@ We build the binary and check its correctness and performance.
 
  .. code-block:: none
 
-    Execution time of this operator: 0.334 ms
+    Execution time of this operator: 0.319 ms
 
 
 
@@ -393,9 +693,9 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
     conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
     conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
     conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
-    conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
-    conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=8)
-    conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=1)
+    conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
+    conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=4)
+    conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=2)
     conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
     conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
     conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
@@ -405,18 +705,18 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
     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=4)
-    conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
+    conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=1)
+    conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
     conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
-    conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
-    conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
+    conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
+    conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
     conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
     s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
     compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
     compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
     compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
     compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=8)
-    compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=1)
+    compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=2)
     compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
     compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
     compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
@@ -442,14 +742,14 @@ 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=49)
+    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=98)
     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=49)
+    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=98)
     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", 16)
+    s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
     s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
 
     CUDA source code:
@@ -467,10 +767,10 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
       #define int64_t long long
       #define uint64_t unsigned long long
     #endif
-    extern "C" __global__ void __launch_bounds__(49) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+    extern "C" __global__ void __launch_bounds__(98) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
       float conv2d_nchw[8];
       __shared__ float pad_temp_shared[252];
-      __shared__ float kernel_shared[96];
+      __shared__ float kernel_shared[192];
       conv2d_nchw[0] = 0.000000e+00f;
       conv2d_nchw[1] = 0.000000e+00f;
       conv2d_nchw[2] = 0.000000e+00f;
@@ -480,33 +780,330 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
       conv2d_nchw[6] = 0.000000e+00f;
       conv2d_nchw[7] = 0.000000e+00f;
       for (int rc_outer_outer = 0; rc_outer_outer < 128; ++rc_outer_outer) {
-        for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
-          __syncthreads();
-          pad_temp_shared[((int)threadIdx.x)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 196) + ((int)threadIdx.x)) + rx_outer_outer) - 8)] : 0.000000e+00f);
-          pad_temp_shared[(((int)threadIdx.x) + 49)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 49) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
-          pad_temp_shared[(((int)threadIdx.x) + 98)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 98) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
-          pad_temp_shared[(((int)threadIdx.x) + 147)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 147) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
-          pad_temp_shared[(((int)threadIdx.x) + 196)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 196) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
-          if (((int)threadIdx.x) < 7) {
-            pad_temp_shared[(((int)threadIdx.x) + 245)] = 0.000000e+00f;
-          }
-          kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) % 12) * 3)) + rx_outer_outer)];
-          if (((int)threadIdx.x) < 47) {
-            kernel_shared[(((int)threadIdx.x) + 49)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 49) / 12) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 1) % 12) * 3)) + rx_outer_outer)];
-          }
-          __syncthreads();
-          for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
-            for (int ff_outer_inner = 0; ff_outer_inner < 8; ++ff_outer_inner) {
-              conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[((ry_outer_inner * 7) + ((int)threadIdx.x))] * kernel_shared[((ff_outer_inner * 12) + ry_outer_inner)]));
-              conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((ry_outer_inner * 7) + ((int)threadIdx.x)) + 63)] * kernel_shared[(((ff_outer_inner * 12) + ry_outer_inner) + 3)]));
-              conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((ry_outer_inner * 7) + ((int)threadIdx.x)) + 126)] * kernel_shared[(((ff_outer_inner * 12) + ry_outer_inner) + 6)]));
-              conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((ry_outer_inner * 7) + ((int)threadIdx.x)) + 189)] * kernel_shared[(((ff_outer_inner * 12) + ry_outer_inner) + 9)]));
-            }
-          }
+        __syncthreads();
+        pad_temp_shared[((int)threadIdx.x)] = ((((9 <= (((int)threadIdx.x) % 63)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+        pad_temp_shared[(((int)threadIdx.x) + 98)] = ((((9 <= ((((int)threadIdx.x) + 35) % 63)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 98) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+        if (((int)threadIdx.x) < 56) {
+          pad_temp_shared[(((int)threadIdx.x) + 196)] = ((((2 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 196) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
         }
+        kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) % 12) / 3) * 9)) + (((int)threadIdx.x) % 3))];
+        if (((int)threadIdx.x) < 94) {
+          kernel_shared[(((int)threadIdx.x) + 98)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 98) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 2) % 12) / 3) * 9)) + ((((int)threadIdx.x) + 2) % 3))];
+        }
+        __syncthreads();
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[((((int)threadIdx.x) / 49) * 96)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 12)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 1)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 13)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 2)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 14)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 24)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 36)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 25)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 37)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 26)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 38)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 48)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 60)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 49)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 61)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 50)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 62)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 72)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 84)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 73)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 85)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 74)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 86)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 3)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 15)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 4)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 16)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 5)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 17)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 27)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 39)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 28)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 40)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 29)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 41)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 51)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 63)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 52)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 64)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 53)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 65)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 75)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 87)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 76)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 88)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 77)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 89)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 6)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 18)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 7)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 19)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 8)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 20)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 30)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 42)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 31)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 43)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 32)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 44)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 54)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 66)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 55)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 67)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 56)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 68)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 78)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 90)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 79)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 91)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 80)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 92)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 9)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 21)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 10)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 22)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 11)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 23)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 33)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 45)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 34)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 46)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 35)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 47)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 57)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 69)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 58)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 70)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 59)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 71)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 81)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 93)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 82)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 94)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 83)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 95)]));
+        __syncthreads();
+        pad_temp_shared[((int)threadIdx.x)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 1)] : 0.000000e+00f);
+        pad_temp_shared[(((int)threadIdx.x) + 98)] = (((1 <= ((((int)threadIdx.x) + 8) % 9)) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 98) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 1)] : 0.000000e+00f);
+        if (((int)threadIdx.x) < 56) {
+          pad_temp_shared[(((int)threadIdx.x) + 196)] = (((1 <= ((((int)threadIdx.x) + 7) % 9)) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 196) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 1)] : 0.000000e+00f);
+        }
+        kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) % 12) / 3) * 9)) + (((int)threadIdx.x) % 3)) + 3)];
+        if (((int)threadIdx.x) < 94) {
+          kernel_shared[(((int)threadIdx.x) + 98)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 98) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 2) % 12) / 3) * 9)) + ((((int)threadIdx.x) + 2) % 3)) + 3)];
+        }
+        __syncthreads();
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[((((int)threadIdx.x) / 49) * 96)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 12)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 1)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 13)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 2)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 14)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 24)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 36)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 25)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 37)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 26)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 38)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 48)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 60)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 49)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 61)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 50)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 62)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 72)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 84)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 73)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 85)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 74)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 86)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 3)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 15)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 4)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 16)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 5)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 17)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 27)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 39)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 28)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 40)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 29)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 41)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 51)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 63)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 52)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 64)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 53)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 65)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 75)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 87)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 76)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 88)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 77)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 89)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 6)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 18)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 7)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 19)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 8)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 20)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 30)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 42)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 31)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 43)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 32)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 44)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 54)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 66)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 55)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 67)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 56)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 68)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 78)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 90)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 79)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 91)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 80)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 92)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 9)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 21)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 10)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 22)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 11)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 23)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 33)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 45)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 34)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 46)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 35)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 47)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 57)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 69)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 58)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 70)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 59)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 71)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 81)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 93)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 82)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 94)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 83)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 95)]));
+        __syncthreads();
+        pad_temp_shared[((int)threadIdx.x)] = (((((((int)threadIdx.x) % 63) < 54) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) + 6)] : 0.000000e+00f);
+        pad_temp_shared[(((int)threadIdx.x) + 98)] = ((((((((int)threadIdx.x) + 35) % 63) < 54) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 98) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) + 6)] : 0.000000e+00f);
+        if (((int)threadIdx.x) < 56) {
+          pad_temp_shared[(((int)threadIdx.x) + 196)] = ((((((int)threadIdx.x) < 47) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 196) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) + 6)] : 0.000000e+00f);
+        }
+        kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) % 12) / 3) * 9)) + (((int)threadIdx.x) % 3)) + 6)];
+        if (((int)threadIdx.x) < 94) {
+          kernel_shared[(((int)threadIdx.x) + 98)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 98) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 2) % 12) / 3) * 9)) + ((((int)threadIdx.x) + 2) % 3)) + 6)];
+        }
+        __syncthreads();
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[((((int)threadIdx.x) / 49) * 96)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 12)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 1)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 13)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 2)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 14)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 24)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 36)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 25)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 37)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 26)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 38)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 48)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 60)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 49)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 61)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 50)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 62)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 72)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 84)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 73)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 85)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 74)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 86)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 3)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 15)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 4)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 16)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 5)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 17)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 27)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 39)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 28)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 40)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 29)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 41)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 51)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 63)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 52)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 64)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 53)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 65)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 75)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 87)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 76)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 88)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 77)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 89)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 6)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 18)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 7)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 19)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 8)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 20)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 30)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 42)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 31)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 43)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 32)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 44)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 54)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 66)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 55)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 67)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 56)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 68)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 78)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 90)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 79)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 91)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 80)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 92)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 9)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 21)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 10)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 22)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 11)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 23)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 33)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 45)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 34)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 46)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 35)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 47)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 57)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 69)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 58)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 70)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 59)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 71)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 81)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 93)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 82)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 94)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 83)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 95)]));
       }
       for (int i1_inner = 0; i1_inner < 8; ++i1_inner) {
-        compute[(((((int)blockIdx.x) * 392) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 8) + i1_inner)]), 0.000000e+00f);
+        compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 49) * 392)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 49) * 8)) + i1_inner)]), 0.000000e+00f);
       }
     }
 
@@ -568,7 +1165,7 @@ In the example below we resume the status and do more 5 trials.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 5 minutes  35.577 seconds)
+   **Total running time of the script:** ( 5 minutes  36.234 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 6b5d4e3713..9e42c42a8f 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -647,7 +647,7 @@ so we can read the log file and load the best schedules.
     Evaluate inference time cost...
     Execution time summary:
      mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)  
-       7.8537       7.8488       7.8643       7.8479       0.0075   
+       7.8445       7.8400       7.8543       7.8393       0.0069   
                
 
 
@@ -675,7 +675,7 @@ Other Tips
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  6.985 seconds)
+   **Total running time of the script:** ( 1 minutes  6.080 seconds)
 
 
 .. _sphx_glr_download_how_to_tune_with_autoscheduler_tune_network_cuda.py:
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
index 0cf037e20b..46dfec3bfc 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)  
-      763.4786     763.5029     764.6758     762.2570      0.9876   
+      753.6344     752.6742     755.7805     752.4486      1.5203   
                
 
 
@@ -694,7 +694,7 @@ Other Tips
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  40.746 seconds)
+   **Total running time of the script:** ( 1 minutes  39.092 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 c8e1080ef9..7d339b6e34 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
@@ -392,13 +392,13 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
             placeholder_8 = T.match_buffer(placeholder_3, (33,), "int32")
             placeholder_9 = T.match_buffer(placeholder_4, (128, 512))
             compute_1 = T.match_buffer(compute, (128, 512))
-            for i0_outer_i1_outer_fused in T.parallel(256):
-                compute_2 = T.allocate([256], "float32", "global")
-                compute_3 = T.buffer_decl((256,), data=compute_2)
+            for i0_outer_i1_outer_fused in T.parallel(128):
+                compute_2 = T.allocate([512], "float32", "global")
+                compute_3 = T.buffer_decl((512,), data=compute_2)
                 for nb_j_inner in range(2):
-                    for i_inner_init, j_init in T.grid(8, 16):
+                    for i_inner_init, j_init in T.grid(16, 16):
                         compute_3[i_inner_init * 32 + nb_j_inner * 16 + j_init] = T.float32(0)
-                    for elem_idx, i_inner, j in T.grid(T.let(cse_var_1, i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner, placeholder_10[cse_var_1 + 1] - placeholder_10[cse_var_1]), 8, 16):
+                    for elem_idx, i_inner, j in T.grid(T.let(cse_var_1, i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner, placeholder_10[cse_var_1 + 1] - placeholder_10[cse_var_1]), 16, 16):
                         cse_var_1 = T.var("int32")
                         placeholder_10 = T.buffer_decl((33,), "int32", data=placeholder_8.data)
                         cse_var_3: T.int32 = i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner
@@ -406,12 +406,12 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
                         placeholder_11 = T.buffer_decl((78656,), data=placeholder_6.data)
                         placeholder_12 = T.buffer_decl((32768,), data=placeholder_5.data)
                         placeholder_13 = T.buffer_decl((4916,), "int32", data=placeholder_7.data)
-                        compute_3[cse_var_2] = compute_3[cse_var_2] + placeholder_11[placeholder_10[cse_var_3] * 16 + elem_idx * 16 + j] * T.max(placeholder_12[i0_outer_i1_outer_fused // 16 * 2048 + i_inner * 256 + placeholder_13[placeholder_10[cse_var_3] + elem_idx]], T.float32(0))
-                for i0_inner in range(8):
-                    cse_var_4: T.int32 = i0_outer_i1_outer_fused // 16 * 4096 + i0_inner * 512 + i0_outer_i1_outer_fused % 16 * 32
+                        compute_3[cse_var_2] = compute_3[cse_var_2] + placeholder_11[placeholder_10[cse_var_3] * 16 + elem_idx * 16 + j] * T.max(placeholder_12[i0_outer_i1_outer_fused // 16 * 4096 + i_inner * 256 + placeholder_13[placeholder_10[cse_var_3] + elem_idx]], T.float32(0))
+                for i0_inner, i1_inner in T.grid(16, 32):
+                    cse_var_4: T.int32 = i0_outer_i1_outer_fused // 16 * 8192 + i0_inner * 512 + i0_outer_i1_outer_fused % 16 * 32 + i1_inner
                     compute_4 = T.buffer_decl((65536,), data=compute_1.data)
                     placeholder_10 = T.buffer_decl((65536,), data=placeholder_9.data)
-                    compute_4[cse_var_4:cse_var_4 + 32] = T.max(compute_3[i0_inner * 32:i0_inner * 32 + 32] + placeholder_10[cse_var_4:cse_var_4 + 32], T.Broadcast(T.float32(0), 32))
+                    compute_4[cse_var_4] = T.max(compute_3[i0_inner * 32 + i1_inner] + placeholder_10[cse_var_4], T.float32(0))
 
 
 
@@ -461,7 +461,7 @@ We build the binary and check its correctness and performance.
 
  .. code-block:: none
 
-    Execution time of this operator: 1.658 ms
+    Execution time of this operator: 1.528 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 579c1f6807..293285cb06 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
@@ -5,16 +5,16 @@
 
 Computation times
 =================
-**00:47.104** total execution time for **how_to_tune_with_autotvm** files:
+**00:32.631** 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``)           | 00:47.070 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)           | 00:32.597 | 0.0 MB |
 +--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)               | 00:00.020 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)               | 00:00.021 | 0.0 MB |
 +--------------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``)             | 00:00.005 | 0.0 MB |
 +--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``)               | 00:00.005 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``)               | 00:00.004 | 0.0 MB |
 +--------------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``) | 00:00.004 | 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 ad9a8b8bf3..e6441b6242 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
@@ -268,27 +268,7 @@ for this template
     waiting for device...
     device available
     Get devices for measurement successfully!
-    No: 1   GFLOPS: 4.06/4.06       result: MeasureResult(costs=(0.0569717215,), error_no=MeasureErrorNo.NO_ERROR, all_cost=7.68753981590271, timestamp=1674075708.6732135) [('tile_f', [-1, 2, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10272631
-    No: 2   GFLOPS: 0.00/4.06       result: Traceback (most recent call last):
-      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
-        res = future.result()
-      File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
-        return self.__get_result()
-      File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
-        raise self._exception
-      File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
-        result = self.fn(*self.args, **self.kwargs)
-      File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
-        worker = lambda *args: self._worker_run(*args)
-      File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
-        return proc.recv()
-      File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
-        raise TimeoutError()
-    TimeoutError
-
-            [('tile_f', [-1, 32, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9172793
-    No: 3   GFLOPS: 70.10/70.10     result: MeasureResult(costs=(0.0033024939032258067,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.2502856254577637, timestamp=1674075710.3525412)      [('tile_f', [-1, 4, 16, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4465867
-    No: 4   GFLOPS: 0.00/70.10      result: Traceback (most recent call last):
+    No: 1   GFLOPS: 0.00/0.00       result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -410,8 +390,8 @@ for this template
       File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 4, 1, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9208522
-    No: 5   GFLOPS: 0.00/70.10      result: Traceback (most recent call last):
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 8, 8, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8688804
+    No: 2   GFLOPS: 0.00/0.00       result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -533,8 +513,10 @@ for this template
       File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 64, 2, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5091574
-    No: 6   GFLOPS: 0.00/70.10      result: Traceback (most recent call last):
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 256, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8247863
+    No: 3   GFLOPS: 6.58/6.58       result: MeasureResult(costs=(0.035200592,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7256617546081543, timestamp=1674083387.1573093)        [('tile_f', [-1, 16, 2, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2778052
+    No: 4   GFLOPS: 424.77/424.77   result: MeasureResult(costs=(0.0005450040850340136,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8987197875976562, timestamp=1674083388.1656663)      [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6048699
+    No: 5   GFLOPS: 0.00/424.77     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -656,8 +638,9 @@ for this template
       File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 16, 2, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4177692
-    No: 7   GFLOPS: 0.00/70.10      result: Traceback (most recent call last):
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 4, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10176552
+    No: 6   GFLOPS: 6.20/424.77     result: MeasureResult(costs=(0.0373385695,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.085918426513672, timestamp=1674083391.4190078)        [('tile_f', [-1, 2, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1655511
+    No: 7   GFLOPS: 0.00/424.77     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -779,8 +762,9 @@ for this template
       File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 1, 64, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6955174
-    No: 8   GFLOPS: 0.00/70.10      result: Traceback (most recent call last):
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 16, 16, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,482329
+    No: 8   GFLOPS: 326.31/424.77   result: MeasureResult(costs=(0.0007094430223214285,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.420546054840088, timestamp=1674083393.400589)        [('tile_f', [-1, 1, 2, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,723864
+    No: 9   GFLOPS: 0.00/424.77     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -902,8 +886,10 @@ for this template
       File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 1, 16, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9552558
-    No: 9   GFLOPS: 0.00/70.10      result: Traceback (most recent call last):
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 8, 4, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2246055
+    No: 10  GFLOPS: 3.03/424.77     result: MeasureResult(costs=(0.076422142,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0677151679992676, timestamp=1674083400.2040286)        [('tile_f', [-1, 4, 2, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,264852
+    No: 11  GFLOPS: 5.79/424.77     result: MeasureResult(costs=(0.0399865835,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.994432687759399, timestamp=1674083401.1428769)        [('tile_f', [-1, 2, 1, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5139557
+    No: 12  GFLOPS: 0.00/424.77     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1025,8 +1011,8 @@ for this template
       File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 1, 8, 64]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9706829
-    No: 10  GFLOPS: 0.00/70.10      result: Traceback (most recent call last):
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 1, 128, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5695457
+    No: 13  GFLOPS: 0.00/424.77     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1148,8 +1134,8 @@ for this template
       File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9816963
-    No: 11  GFLOPS: 0.00/70.10      result: Traceback (most recent call last):
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 4, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8164872
+    No: 14  GFLOPS: 0.00/424.77     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1271,8 +1257,8 @@ for this template
       File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 2, 2, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1345931
-    No: 12  GFLOPS: 0.00/70.10      result: Traceback (most recent call last):
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 4, 2, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1712986
+    No: 15  GFLOPS: 0.00/424.77     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1394,8 +1380,8 @@ for this template
       File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 8, 16, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4333157
-    No: 13  GFLOPS: 0.00/70.10      result: Traceback (most recent call last):
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 16, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4603888
+    No: 16  GFLOPS: 0.00/424.77     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1517,8 +1503,8 @@ for this template
       File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 4, 4, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10156231
-    No: 14  GFLOPS: 0.00/70.10      result: Traceback (most recent call last):
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 128, 2, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,911971
+    No: 17  GFLOPS: 0.00/424.77     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1640,8 +1626,8 @@ for this template
       File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 8, 8, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9417402
-    No: 15  GFLOPS: 0.00/70.10      result: Traceback (most recent call last):
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 8, 8, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5438337
+    No: 18  GFLOPS: 0.00/424.77     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1763,9 +1749,8 @@ for this template
       File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 2, 1, 128]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1381151
-    No: 16  GFLOPS: 309.06/309.06   result: MeasureResult(costs=(0.0007490498333333333,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.328589677810669, timestamp=1674075715.4546165)       [('tile_f', [-1, 2, 4, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1790213
-    No: 17  GFLOPS: 0.00/309.06     result: Traceback (most recent call last):
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3870224
+    No: 19  GFLOPS: 0.00/424.77     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1887,161 +1872,8 @@ for this template
       File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 4, 2, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3962750
-    No: 18  GFLOPS: 0.00/309.06     result: Traceback (most recent call last):
-      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 742, in __call__
-        yield remote, remote.load_module(os.path.split(build_result.filename)[1])
-      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
-        costs = time_f(*args).results
-      File "/workspace/python/tvm/runtime/module.py", line 357, in evaluator
-        blob = feval(*args)
-      File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
-      File "tvm/_ffi/_cython/./packed_func.pxi", line 262, in tvm._ffi._cy3.core.FuncCall
-      File "tvm/_ffi/_cython/./packed_func.pxi", line 251, in tvm._ffi._cy3.core.FuncCall3
-      File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
-    tvm._ffi.base.TVMError: Traceback (most recent call last):
-      4: TVMFuncCall
-            at ../src/runtime/c_runtime_api.cc:477
-      3: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
-            at ../include/tvm/runtime/packed_func.h:1217
-      2: tvm::runtime::RPCWrappedFunc::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
-            at ../src/runtime/rpc/rpc_module.cc:129
-      1: tvm::runtime::RPCClientSession::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)> const&)
-            at ../src/runtime/rpc/rpc_endpoint.cc:1012
-      0: tvm::runtime::RPCEndpoint::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)>)
-            at ../src/runtime/rpc/rpc_endpoint.cc:804
-      File "../src/runtime/rpc/rpc_endpoint.cc", line 804
-    TVMError: 
-    ---------------------------------------------------------------
-    An error occurred during the execution of TVM.
-    For more information, please see: https://tvm.apache.org/docs/errors.html
-    ---------------------------------------------------------------
-      Check failed: (code == RPCCode::kReturn) is false: code=kShutdown
-
-    During handling of the above exception, another exception occurred:
-
-    Traceback (most recent call last):
-      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
-        costs = time_f(*args).results
-      File "/usr/lib/python3.7/contextlib.py", line 130, in __exit__
-        self.gen.throw(type, value, traceback)
-      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 746, in __call__
-        remote.remove(build_result.filename)
-      File "/workspace/python/tvm/rpc/client.py", line 144, in remove
-        self._remote_funcs["remove"] = self.get_function("tvm.rpc.server.remove")
-      File "/workspace/python/tvm/rpc/client.py", line 72, in get_function
-        return self._sess.get_function(name)
-      File "/workspace/python/tvm/runtime/module.py", line 171, in get_function
-        self.handle, c_str(name), ctypes.c_int(query_imports), ctypes.byref(ret_handle)
-      File "/workspace/python/tvm/_ffi/base.py", line 348, in check_call
-        raise get_last_ffi_error()
-    tvm._ffi.base.TVMError: Traceback (most recent call last):
-      52: 0xffffffffffffffff
-      51: _start
-      50: __libc_start_main
-      49: _Py_UnixMain
-      48: 0x0000000000650da0
-      47: 0x0000000000650afa
-      46: _PyFunction_FastCallDict
-      45: _PyEval_EvalCodeWithName
-      44: _PyEval_EvalFrameDefault
-      43: _PyFunction_FastCallKeywords
-      42: _PyEval_EvalCodeWithName
-      41: _PyEval_EvalFrameDefault
-      40: _PyMethodDef_RawFastCallKeywords
-      39: 0x0000000000546369
-      38: _PyEval_EvalCodeWithName
-      37: _PyEval_EvalFrameDefault
-      36: _PyFunction_FastCallKeywords
-      35: _PyEval_EvalCodeWithName
-      34: _PyEval_EvalFrameDefault
-      33: _PyFunction_FastCallDict
-      32: _PyEval_EvalCodeWithName
-      31: _PyEval_EvalFrameDefault
-      30: _PyObject_FastCallDict
-      29: 0x00000000004c06e1
-      28: _PyFunction_FastCallDict
-      27: _PyEval_EvalFrameDefault
-      26: _PyMethodDescr_FastCallKeywords
-      25: 0x00000000005dcb58
-      24: 0x00000000005dc83f
-      23: 0x00000000004ba127
-      22: _PyEval_EvalFrameDefault
-      21: _PyFunction_FastCallKeywords
-      20: _PyEval_EvalFrameDefault
-      19: _PyFunction_FastCallKeywords
-      18: _PyEval_EvalFrameDefault
-      17: _PyFunction_FastCallKeywords
-      16: _PyEval_EvalCodeWithName
-      15: _PyEval_EvalFrameDefault
-      14: 0x0000000000537c30
-      13: _PyObject_FastCallKeywords
-      12: 0x00007f95138f1fa2
-      11: _ctypes_callproc
-      10: ffi_call
-      9: ffi_call_unix64
-      8: TVMModGetFunction
-            at ../src/runtime/c_runtime_api.cc:408
-      7: tvm::runtime::ModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, bool)
-            at ../src/runtime/module.cc:66
-      6: tvm::runtime::RPCModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)
-            at ../src/runtime/rpc/rpc_module.cc:185
-      5: tvm::runtime::RPCClientSession::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
-            at ../src/runtime/rpc/rpc_endpoint.cc:1007
-      4: tvm::runtime::TVMRetValue tvm::runtime::RPCEndpoint::SysCallRemote<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(tvm::runtime::RPCCode, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
-            at ../src/runtime/rpc/rpc_endpoint.h:223
-      3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(int&&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) const
-            at ../include/tvm/runtime/packed_func.h:1617
-      2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
-            at ../include/tvm/runtime/packed_func.h:1217
-      1: Call
-            at ../include/tvm/runtime/packed_func.h:1213
-      0: operator()
-            at ../src/runtime/rpc/rpc_endpoint.cc:684
-      File "../src/runtime/rpc/rpc_endpoint.cc", line 684
-    TVMError: 
-    ---------------------------------------------------------------
-    An error occurred during the execution of TVM.
-    For more information, please see: https://tvm.apache.org/docs/errors.html
-    ---------------------------------------------------------------
-      Check failed: (code == RPCCode::kReturn) is false: code=1
-
-    Traceback (most recent call last):
-      52: 0xffffffffffffffff
-      51: _start
-      50: __libc_start_main
-      49: _Py_UnixMain
-      48: 0x0000000000650da0
-      47: 0x0000000000650afa
-      46: _PyFunction_FastCallDict
-      45: _PyEval_EvalCodeWithName
-      44: _PyEval_EvalFrameDefault
-      43: _PyFunction_FastCallKeywords
-      42: _PyEval_EvalCodeWithName
-      41: _PyEval_EvalFrameDefault
-      40: _PyMethodDef_RawFastCallKeywords
-      39: 0x0000000000546369
-      38: _PyEval_EvalCodeWithName
-      37: _PyEval_EvalFrameDefault
-      36: _PyFunction_FastCallKeywords
-      35: _PyEval_EvalCodeWithName
-      34: _PyEval_EvalFrameDefault
-      33: _PyFunction_FastCallDict
-      32: _PyEval_EvalCodeWithName
-      31: _PyEval_EvalFrameDefault
-      30: _PyObject_FastCallDict
-      29: 0x00000000004c06e1
-      28: _PyFunction_FastCallDict
-      27: _PyEval_EvalFrameDefault
-      26: _PyMethodDescr_FastCallKeywords
-      25: 0x00000000005dcb58
-      24: 0x00000000005dc83f
-      23: 0x00000000004ba127
-      22: _PyEval_EvalFrameDefault
-      21: _PyFunction_FastCallKeywords
-      20: _PyEval_EvalFrameDefault
-      19: _PyFunction_FastCall      [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,750640
-    No: 19  GFLOPS: 0.00/309.06     result: Traceback (most recent call last):
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 4, 32, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3353552
+    No: 20  GFLOPS: 0.00/424.77     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2163,8 +1995,7 @@ for this template
       File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3314046
-    No: 20  GFLOPS: 30.02/309.06    result: MeasureResult(costs=(0.007710311230769231,), error_no=MeasureErrorNo.NO_ERROR, all_cost=10.001625537872314, timestamp=1674075730.2298257)       [('tile_f', [-1, 1, 1, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3568365
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 4, 1, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2127402
 
 
 
@@ -2219,9 +2050,9 @@ and measure running time.
     Finish loading 20 records
 
     Best config:
-    [('tile_f', [-1, 2, 4, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1790213
+    [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6048699
     Finish loading 20 records
-    Time cost of this operator: 0.001066
+    Time cost of this operator: 0.000883
 
 
 
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 766d7d80b0..ed55e357a2 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
@@ -363,10 +363,10 @@ 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  311.5     98.719   (1, 2, 10, 10, 3)  2       1        [311.5]           
-    tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       3.071     0.973    (1, 6, 10, 10)     1       1        [3.071]           
-    tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.97      0.308    (1, 1, 10, 10, 3)  1       1        [0.97]            
-    Total_time                                    -                                             315.541   -        -                  -       -        -                 
+    tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  312.4     98.732   (1, 2, 10, 10, 3)  2       1        [312.4]           
+    tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       3.024     0.956    (1, 6, 10, 10)     1       1        [3.024]           
+    tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.988     0.312    (1, 1, 10, 10, 3)  1       1        [0.988]           
+    Total_time                                    -                                             316.412   -        -                  -       -        -                 
 
 
 
@@ -431,10 +431,10 @@ 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  134.4     97.944   (1, 6, 10, 10, 1)  2       1        [134.4]           
-    tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       1.833     1.336    (1, 6, 10, 10)     1       1        [1.833]           
-    tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.987     0.72     (1, 1, 10, 10, 3)  1       1        [0.987]           
-    Total_time                                    -                                             137.221   -        -                  -       -        -                 
+    tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  109.3     97.657   (1, 6, 10, 10, 1)  2       1        [109.3]           
+    tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       1.775     1.586    (1, 6, 10, 10)     1       1        [1.775]           
+    tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.847     0.757    (1, 3, 10, 10, 1)  1       1        [0.847]           
+    Total_time                                    -                                             111.923   -        -                  -       -        -                 
 
 
 
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
index 7db93b2141..4c729eec01 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
@@ -117,7 +117,7 @@ download a cat image and preprocess it to use as the model input.
     /venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/ao/quantization/utils.py:281: UserWarning: must run observer before calling calculate_qparams. Returning default values.
       "must run observer before calling calculate_qparams. " +
     Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
-
      0%|          | 0.00/3.42M [00:00<?, ?B/s]
    100%|##########| 3.42M/3.42M [00:00<00:00, 45.9MB/s]
+
      0%|          | 0.00/3.42M [00:00<?, ?B/s]
     61%|######    | 2.09M/3.42M [00:00<00:00, 21.1MB/s]
    100%|##########| 3.42M/3.42M [00:00<00:00, 32.5MB/s]
     /workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
       return LooseVersion(torch_ver) > ver
     /venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -322,7 +322,7 @@ Look up prediction top 1 index in 1000 class synset.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  11.832 seconds)
+   **Total running time of the script:** ( 1 minutes  10.557 seconds)
 
 
 .. _sphx_glr_download_how_to_work_with_microtvm_micro_pytorch.py:
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
index ade5de6d81..3918cf5325 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
@@ -218,7 +218,7 @@ take about **2 minutes** to download the Stanford Cars, while COCO 2017 validati
  .. code-block:: none
 
 
-    '/tmp/tmpkzt99nrx/images/random'
+    '/tmp/tmp7s9ljeud/images/random'
 
 
 
@@ -309,7 +309,7 @@ objects to other stuff? We can display some examples from our datasets using ``m
 
 
 .. image-sg:: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
-   :alt: [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0]
+   :alt: [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0]
    :srcset: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
    :class: sphx-glr-single-img
 
@@ -318,8 +318,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
 
  .. code-block:: none
 
-    /tmp/tmpkzt99nrx/images/target contains 8144 images
-    /tmp/tmpkzt99nrx/images/random contains 5000 images
+    /tmp/tmp7s9ljeud/images/target contains 8144 images
+    /tmp/tmp7s9ljeud/images/random contains 5000 images
 
 
 
@@ -494,13 +494,13 @@ the time on our validation set).
  .. code-block:: none
 
     Epoch 1/3
-    328/328 - 47s - loss: 0.2224 - accuracy: 0.9233 - val_loss: 0.1460 - val_accuracy: 0.9471 - 47s/epoch - 144ms/step
+    328/328 - 47s - loss: 0.2046 - accuracy: 0.9263 - val_loss: 0.1429 - val_accuracy: 0.9569 - 47s/epoch - 144ms/step
     Epoch 2/3
-    328/328 - 44s - loss: 0.0965 - accuracy: 0.9635 - val_loss: 0.1448 - val_accuracy: 0.9532 - 44s/epoch - 133ms/step
+    328/328 - 44s - loss: 0.0962 - accuracy: 0.9633 - val_loss: 0.1475 - val_accuracy: 0.9524 - 44s/epoch - 133ms/step
     Epoch 3/3
-    328/328 - 44s - loss: 0.0757 - accuracy: 0.9742 - val_loss: 0.1207 - val_accuracy: 0.9585 - 44s/epoch - 133ms/step
+    328/328 - 44s - loss: 0.0661 - accuracy: 0.9755 - val_loss: 0.1311 - val_accuracy: 0.9622 - 44s/epoch - 133ms/step
 
-    <keras.callbacks.History object at 0x7f43f4bcb450>
+    <keras.callbacks.History object at 0x7fb54fc009d0>
 
 
 
@@ -857,7 +857,7 @@ Arduino tutorial for how to do that `on GitHub <https://github.com/guberti/tvm-a
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 5 minutes  6.318 seconds)
+   **Total running time of the script:** ( 5 minutes  12.154 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 10154a759b..35bf8b0de9 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
 
 Computation times
 =================
-**07:24.742** total execution time for **how_to_work_with_microtvm** files:
+**07:28.452** total execution time for **how_to_work_with_microtvm** files:
 
 +---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``)               | 05:06.318 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``)               | 05:12.154 | 0.0 MB |
 +---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``)           | 01:11.832 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``)           | 01:10.557 | 0.0 MB |
 +---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)         | 00:53.832 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)         | 00:52.901 | 0.0 MB |
 +---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``)                   | 00:08.773 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``)                   | 00:08.926 | 0.0 MB |
 +---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)             | 00:03.987 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)             | 00:03.914 | 0.0 MB |
 +---------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``)             | 00:00.000 | 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 15a938d395..efeb170284 100644
--- a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
 
 Computation times
 =================
-**00:45.287** total execution time for **how_to_work_with_relay** files:
+**00:45.233** 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``) | 00:32.667 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:33.298 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)           | 00:10.208 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)           | 00:10.387 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)                             | 00:02.406 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)                             | 00:01.542 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``)                 | 00:00.006 | 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 ed02247e2a..f7457490ec 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
@@ -264,7 +264,7 @@ The following example customizes CUDA lowering rule for :code:`exp`.
  .. code-block:: none
 
 
-    <function my_cuda_math_rule at 0x7f436d0af3b0>
+    <function my_cuda_math_rule at 0x7fb54faeb3b0>
 
 
 
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 6d47654d76..bff7427c1c 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
 =================
-**00:04.601** total execution time for **how_to_work_with_schedules** files:
+**00:08.046** total execution time for **how_to_work_with_schedules** files:
 
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)                 | 00:02.230 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)                 | 00:05.510 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)                     | 00:01.051 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)                     | 00:01.152 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)                     | 00:00.546 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)                     | 00:00.591 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)                               | 00:00.545 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)                               | 00:00.568 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)                     | 00:00.118 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)                     | 00:00.117 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.053 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.050 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)                               | 00:00.032 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)                               | 00:00.033 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``)               | 00:00.025 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
index cae7656e65..99f2316784 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -340,7 +340,7 @@ The importing needs to happen before the tensorized GEMV being executed.
             B_1 = T.match_buffer(B, (512, 64))
             C_1 = T.match_buffer(C, (1024, 512))
             i = T.var("int32")
-            T.attr(T.iter_var(i, None, "DataPar", ""), "pragma_import_llvm", "; ModuleID = '/tmp/tmpc34m7xbo/input0.cc'\nsource_filename = \"/tmp/tmpc34m7xbo/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 float*, [...]
+            T.attr(T.iter_var(i, None, "DataPar", ""), "pragma_import_llvm", "; ModuleID = '/tmp/tmpovo8qjzw/input0.cc'\nsource_filename = \"/tmp/tmpovo8qjzw/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 float*, [...]
             for i, j_outer in T.grid(1024, 32):
                 T.call_extern("int32", "gemv_update", T.tvm_access_ptr(T.type_annotation("float32"), C_1.data, i * 512 + j_outer * 16, 16, 2), T.tvm_access_ptr(T.type_annotation("float32"), A_1.data, i * 64, 64, 1), T.tvm_access_ptr(T.type_annotation("float32"), B_1.data, j_outer * 1024, 1024, 1), 16, 64, 64)
 
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 2a6e5845ce..1f003b74f2 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
 =================
-**00:31.042** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:30.513** total execution time for **topic_vta_tutorials_autotvm** files:
 
 +---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:31.035 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:30.506 | 0.0 MB |
 +---------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``)     | 00:00.007 | 0.0 MB |
 +---------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
index 1f221807a5..04c5bbbc5c 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -293,7 +293,7 @@ The compilation steps are:
       DeprecationWarning,
     /workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the  new recommended usage.
       relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
-    resnet18_v1 inference graph built in 33.52s!
+    resnet18_v1 inference graph built in 32.51s!
 
 
 
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 4416b90f99..c09146511c 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -337,7 +337,7 @@ The compilation steps are:
 
     /workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
       DeprecationWarning,
-    yolov3-tiny inference graph built in 22.73s!
+    yolov3-tiny inference graph built in 22.03s!
 
 
 
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 28888bc493..946f1e32a0 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
 =================
-**01:39.912** total execution time for **topic_vta_tutorials_frontend** files:
+**01:38.379** total execution time for **topic_vta_tutorials_frontend** files:
 
 +------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:50.331 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:49.377 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)           | 00:49.580 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)           | 00:49.002 | 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 e0f2836e08..dd9f3ce59c 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
 =================
-**00:03.060** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.189** total execution time for **topic_vta_tutorials_optimize** files:
 
 +--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)         | 00:02.626 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)         | 00:02.717 | 0.0 MB |
 +--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.434 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.472 | 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 71744607a6..ea706255b5 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
 =================
-**00:00.783** total execution time for **topic_vta_tutorials** files:
+**00:00.837** total execution time for **topic_vta_tutorials** files:
 
 +---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.420 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.447 | 0.0 MB |
 +---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.363 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.390 | 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 e75eaafd79..d7aa297289 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -319,7 +319,7 @@ We build the binary and check its correctness and performance.
 
  .. code-block:: none
 
-    Execution time of this operator: 96.807 ms
+    Execution time of this operator: 93.701 ms
 
 
 
@@ -437,7 +437,7 @@ operations.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  14.063 seconds)
+   **Total running time of the script:** ( 1 minutes  14.570 seconds)
 
 
 .. _sphx_glr_download_tutorial_auto_scheduler_matmul_x86.py:
diff --git a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
index 05d8a8f5ff..cdf8558976 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -454,16 +454,16 @@ reduce variance, we take 5 measurements and average them.
     waiting for device...
     device available
     Get devices for measurement successfully!
-    No: 1   GFLOPS: 12.61/12.61     result: MeasureResult(costs=(0.0212931328,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5927474498748779, timestamp=1674074176.122058)        [('tile_y', [-1, 128]), ('tile_x', [-1, 512])],None,97
-    No: 2   GFLOPS: 10.98/12.61     result: MeasureResult(costs=(0.0244551158,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.636193037033081, timestamp=1674074176.7659247)        [('tile_y', [-1, 256]), ('tile_x', [-1, 32])],None,58
-    No: 3   GFLOPS: 3.64/12.61      result: MeasureResult(costs=(0.07364926799999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4282848834991455, timestamp=1674074178.9988792)        [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
-    No: 4   GFLOPS: 1.55/12.61      result: MeasureResult(costs=(0.17315853939999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.9932665824890137, timestamp=1674074182.8237185)        [('tile_y', [-1, 4]), ('tile_x', [-1, 1])],None,2
-    No: 5   GFLOPS: 4.13/12.61      result: MeasureResult(costs=(0.0650630472,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2994110584259033, timestamp=1674074184.2370825)       [('tile_y', [-1, 16]), ('tile_x', [-1, 16])],None,44
-    No: 6   GFLOPS: 0.83/12.61      result: MeasureResult(costs=(0.32272345839999994,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.410374402999878, timestamp=1674074189.6722739) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
-    No: 7   GFLOPS: 0.89/12.61      result: MeasureResult(costs=(0.299995667,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.033870697021484, timestamp=1674074195.5211098) [('tile_y', [-1, 256]), ('tile_x', [-1, 2])],None,18
-    No: 8   GFLOPS: 9.22/12.61      result: MeasureResult(costs=(0.029109559,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7064783573150635, timestamp=1674074196.2493129)        [('tile_y', [-1, 512]), ('tile_x', [-1, 256])],None,89
-    No: 9   GFLOPS: 1.76/12.61      result: MeasureResult(costs=(0.1522050992,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.6560161113739014, timestamp=1674074199.0208445)       [('tile_y', [-1, 16]), ('tile_x', [-1, 2])],None,14
-    No: 10  GFLOPS: 1.17/12.61      result: MeasureResult(costs=(0.22904607219999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.8800418376922607, timestamp=1674074202.94484)  [('tile_y', [-1, 1]), ('tile_x', [-1, 2])],None,10
+    No: 1   GFLOPS: 1.26/1.26       result: MeasureResult(costs=(0.21366675000000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.6458842754364014, timestamp=1674081857.3550878)        [('tile_y', [-1, 2]), ('tile_x', [-1, 1])],None,1
+    No: 2   GFLOPS: 3.29/3.29       result: MeasureResult(costs=(0.081503407,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5644311904907227, timestamp=1674081859.691211) [('tile_y', [-1, 64]), ('tile_x', [-1, 8])],None,36
+    No: 3   GFLOPS: 1.18/3.29       result: MeasureResult(costs=(0.226755417,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.8612968921661377, timestamp=1674081864.359341) [('tile_y', [-1, 1]), ('tile_x', [-1, 2])],None,10
+    No: 4   GFLOPS: 2.64/3.29       result: MeasureResult(costs=(0.1016112808,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8497552871704102, timestamp=1674081866.2368028)       [('tile_y', [-1, 512]), ('tile_x', [-1, 16])],None,49
+    No: 5   GFLOPS: 3.08/3.29       result: MeasureResult(costs=(0.0872327226,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.637035608291626, timestamp=1674081868.0009913)        [('tile_y', [-1, 256]), ('tile_x', [-1, 8])],None,38
+    No: 6   GFLOPS: 2.67/3.29       result: MeasureResult(costs=(0.10036525700000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8619179725646973, timestamp=1674081869.85988)  [('tile_y', [-1, 2]), ('tile_x', [-1, 16])],None,41
+    No: 7   GFLOPS: 2.10/3.29       result: MeasureResult(costs=(0.12776740339999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.294450283050537, timestamp=1674081872.9340394) [('tile_y', [-1, 128]), ('tile_x', [-1, 4])],None,27
+    No: 8   GFLOPS: 4.03/4.03       result: MeasureResult(costs=(0.066561712,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3215956687927246, timestamp=1674081874.2516136)        [('tile_y', [-1, 4]), ('tile_x', [-1, 16])],None,42
+    No: 9   GFLOPS: 13.20/13.20     result: MeasureResult(costs=(0.020334042400000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5416173934936523, timestamp=1674081874.9080758)       [('tile_y', [-1, 256]), ('tile_x', [-1, 64])],None,68
+    No: 10  GFLOPS: 2.40/13.20      result: MeasureResult(costs=(0.11165571999999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9915447235107422, timestamp=1674081876.9434235)        [('tile_y', [-1, 512]), ('tile_x', [-1, 8])],None,39
 
 
 
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 8a5a4cb010..4a92650a65 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -311,7 +311,7 @@ standard deviation.
 
  .. code-block:: none
 
-    {'mean': 517.6268569099921, 'median': 517.4762197500058, 'std': 2.3963316360720026}
+    {'mean': 518.0414347700003, 'median': 518.4623476000013, 'std': 2.0786998699138803}
 
 
 
@@ -545,31 +545,30 @@ the tuning data to.
 
  .. code-block:: none
 
-
    [Task  1/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  1/25]  Current/Best:   12.38/  13.43 GFLOPS | Progress: (4/20) | 8.99 s
    [Task  1/25]  Current/Best:   14.42/  19.14 GFLOPS | Progress: (8/20) | 12.29 s
    [Task  1/25]  Current/Best:   11.50/  19.14 GFLOPS | Progress: (12/20) | 15.87 s
    [Task  1/25]  Current/Best:   22.84/  23.32 GFLOPS | Progress: (16/20) | 17.99 s
    [Task  1/25]  Current/Best:   13.96/  23.32 GFLOPS | Progress: (20/20) | 20.10 s Done.
-
    [Task  2/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  2/25]  Current/Best:    6.23/  14.51 GFLOPS | Progress: (4/20) | 3.52 s
    [Task  2/25]  Current/Best:   11.90/  14.51 GFLOPS | Progress: (8/20) | 5.41 s
    [Task  2/25]  Current/Best:   10.46/  18.78 GFLOPS | Progress: (12/20) | 8.51 s
    [Task  2/25]  Current/Best:   20.53/  20.53 GFLOPS | Progress: (16/20) | 10.23 s
    [Task  2/25]  Current/Best:    7.61/  20.53 GFLOPS | Progress: (20/20) | 11.80 s Done.
-
    [Task  3/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  3/25]  Current/Best:   12.46/  12.46 GFLOPS | Progress: (4/20) | 5.94 s
    [Task  3/25]  Current/Best:   12.67/  18.78 GFLOPS | Progress: (8/20) | 8.45 s
    [Task  3/25]  Current/Best:   15.14/  20.46 GFLOPS | Progress: (12/20) | 10.77 s
    [Task  3/25]  Current/Best:    6.20/  20.46 GFLOPS | Progress: (16/20) | 13.01 s
    [Task  3/25]  Current/Best:   16.91/  20.46 GFLOPS | Progress: (20/20) | 15.39 s Done.
-
    [Task  4/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  4/25]  Current/Best:   11.45/  15.76 GFLOPS | Progress: (4/20) | 7.30 s
    [Task  4/25]  Current/Best:   12.64/  17.93 GFLOPS | Progress: (8/20) | 10.10 s
    [Task  4/25]  Current/Best:    8.76/  17.93 GFLOPS | Progress: (12/20) | 15.90 s
    [Task  4/25]  Current/Best:    6.43/  17.93 GFLOPS | Progress: (16/20) | 18.57 s
    [Task  4/25]  Current/Best:   16.89/  17.93 GFLOPS | Progress: (20/20) | 21.03 s Done.
-
    [Task  5/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  5/25]  Current/Best:   18.01/  18.01 GFLOPS | Progress: (4/20) | 3.62 s
    [Task  5/25]  Current/Best:   18.07/  18.07 GFLOPS | Progress: (8/20) | 7.33 s
    [Task  5/25]  Current/Best:    9.52/  18.07 GFLOPS | Progress: (12/20) | 10.03 s
    [Task  5/25]  Current/Best:   10.57/  18.07 GFLOPS | Progress: (16/20) | 12.66 s
    [Task  5/25]  Current/Best:   16.99/  18.07 GFLOPS | Progress: (20/20) | 15.13 s Done.
-
    [Task  6/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  6/25]  Current/Best:   10.96/  16.01 GFLOPS | Progress: (4/20) | 5.53 s
    [Task  6/25]  Current/Best:    6.84/  16.01 GFLOPS | Progress: (8/20) | 7.99 s
    [Task  6/25]  Current/Best:   10.68/  16.01 GFLOPS | Progress: (12/20) | 12.24 s
    [Task  6/25]  Current/Best:   17.97/  22.26 GFLOPS | Progress: (16/20) | 19.11 s
    [Task  6/25]  Current/Best:   13.31/  22.26 GFLOPS | Progress: (20/20) | 21.43 s Done.
-
    [Task  7/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  7/25]  Current/Best:   13.79/  19.27 GFLOPS | Progress: (4/20) | 3.98 s
    [Task  7/25]  Current/Best:   19.05/  19.27 GFLOPS | Progress: (8/20) | 6.42 s
    [Task  7/25]  Current/Best:    7.63/  21.17 GFLOPS | Progress: (12/20) | 8.92 s
    [Task  7/25]  Current/Best:    8.05/  21.17 GFLOPS | Progress: (16/20) | 14.09 s
    [Task  7/25]  Current/Best:   15.60/  21.17 GFLOPS | Progress: (20/20) | 16.23 s Done.
-
    [Task  8/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  8/25]  Current/Best:    9.05/  16.66 GFLOPS | Progress: (4/20) | 5.53 s
    [Task  8/25]  Current/Best:    8.12/  16.66 GFLOPS | Progress: (8/20) | 8.94 s
    [Task  8/25]  Current/Best:    8.68/  16.66 GFLOPS | Progress: (12/20) | 13.86 s
    [Task  8/25]  Current/Best:   16.82/  16.82 GFLOPS | Progress: (16/20) | 16.03 s
    [Task  8/25]  Current/Best:    5.17/  16.82 GFLOPS | Progress: (20/20) | 20.09 s Done.
-
    [Task  9/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  9/25]  Current/Best:    8.27/  16.49 GFLOPS | Progress: (4/20) | 6.57 s
    [Task  9/25]  Current/Best:    8.67/  16.49 GFLOPS | Progress: (8/20) | 14.62 s
    [Task  9/25]  Current/Best:   11.92/  21.62 GFLOPS | Progress: (12/20) | 18.17 s
    [Task  9/25]  Current/Best:   18.67/  21.81 GFLOPS | Progress: (16/20) | 21.51 s
    [Task  9/25]  Current/Best:   10.97/  21.81 GFLOPS | Progress: (20/20) | 27.27 s Done.
-
    [Task 10/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 10/25]  Current/Best:   18.67/  18.67 GFLOPS | Progress: (4/20) | 3.52 s
    [Task 10/25]  Current/Best:   10.04/  18.67 GFLOPS | Progress: (8/20) | 5.73 s
    [Task 10/25]  Current/Best:   10.89/  21.60 GFLOPS | Progress: (12/20) | 8.08 s
    [Task 10/25]  Current/Best:   10.22/  21.60 GFLOPS | Progress: (16/20) | 10.71 s
    [Task 10/25]  Current/Best:    7.90/  21.60 GFLOPS | Progress: (20/20) | 13.26 s Done.
-
    [Task 11/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 11/25]  Current/Best:   11.09/  21.19 GFLOPS | Progress: (4/20) | 4.25 s
    [Task 11/25]  Current/Best:   11.26/  21.19 GFLOPS | Progress: (8/20) | 7.12 s
    [Task 11/25]  Current/Best:   11.00/  22.11 GFLOPS | Progress: (12/20) | 10.47 s
    [Task 11/25]  Current/Best:   21.58/  22.11 GFLOPS | Progress: (16/20) | 14.20 s
    [Task 11/25]  Current/Best:   18.65/  22.11 GFLOPS | Progress: (20/20) | 16.86 s Done.
-
    [Task 12/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 12/25]  Current/Best:    7.39/  14.19 GFLOPS | Progress: (4/20) | 7.24 s
    [Task 12/25]  Current/Best:    9.13/  19.32 GFLOPS | Progress: (8/20) | 10.19 s
    [Task 12/25]  Current/Best:   14.48/  21.41 GFLOPS | Progress: (12/20) | 13.42 s
    [Task 12/25]  Current/Best:   11.43/  21.41 GFLOPS | Progress: (16/20) | 15.78 s
    [Task 12/25]  Current/Best:   22.45/  22.45 GFLOPS | Progress: (20/20) | 18.27 s Done.
-
    [Task 13/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 13/25]  Current/Best:   18.44/  21.98 GFLOPS | Progress: (4/20) | 5.49 s
    [Task 13/25]  Current/Best:   12.44/  21.98 GFLOPS | Progress: (8/20) | 7.77 s
    [Task 13/25]  Current/Best:   23.01/  23.01 GFLOPS | Progress: (12/20) | 10.98 s
    [Task 13/25]  Current/Best:    9.27/  23.01 GFLOPS | Progress: (16/20) | 14.93 s
    [Task 13/25]  Current/Best:   17.38/  23.01 GFLOPS | Progress: (20/20) | 17.86 s Done.
-
    [Task 14/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 14/25]  Current/Best:   14.00/  17.87 GFLOPS | Progress: (4/20) | 5.03 s
    [Task 14/25]  Current/Best:    9.01/  18.29 GFLOPS | Progress: (8/20) | 8.95 s
    [Task 14/25]  Current/Best:   10.73/  18.29 GFLOPS | Progress: (12/20) | 12.23 s
    [Task 14/25]  Current/Best:   12.82/  18.29 GFLOPS | Progress: (16/20) | 15.85 s
    [Task 14/25]  Current/Best:   10.89/  18.29 GFLOPS | Progress: (20/20) | 18.61 s
    [Task 15/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 15/25]  Current/Best:    8.50/  18.22 GFLOPS | Progress: (4/20) | 3.50 s
    [Task 15/25]  Current/Best:    9.60/  18.22 GFLOPS | Progress: (8/20) | 7.32 s
    [Task 15/25]  Current/Best:   15.88/  18.22 GFLOPS | Progress: (12/20) | 10.10 s
    [Task 15/25]  Current/Best:   22.26/  22.26 GFLOPS | Progress: (16/20) | 15.06 s
    [Task 15/25]  Current/Best:   14.30/  22.26 GFLOPS | Progress: (20/20
 ) | 17.35 s
    [Task 16/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 16/25]  Current/Best:    9.55/  23.28 GFLOPS | Progress: (4/20) | 4.21 s
    [Task 16/25]  Current/Best:   15.37/  23.28 GFLOPS | Progress: (8/20) | 6.28 s
    [Task 16/25]  Current/Best:   17.33/  23.28 GFLOPS | Progress: (12/20) | 8.48 s
    [Task 16/25]  Current/Best:   14.76/  23.28 GFLOPS | Progress: (16/20) | 10.03 s
    [Task 16/25]  Current/Best:   13.86/  23.28 GFLOPS | Progress: (20/20) | 11.78 s Done.
-
    [Task 17/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 17/25]  Current/Best:   17.62/  17.62 GFLOPS | Progress: (4/20) | 4.75 s
    [Task 17/25]  Current/Best:   17.49/  17.62 GFLOPS | Progress: (8/20) | 8.28 s Done.
+
    [Task  1/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  1/25]  Current/Best:    9.55/  19.13 GFLOPS | Progress: (4/20) | 7.37 s
    [Task  1/25]  Current/Best:   10.09/  19.13 GFLOPS | Progress: (8/20) | 11.14 s
    [Task  1/25]  Current/Best:   12.92/  19.13 GFLOPS | Progress: (12/20) | 14.64 s
    [Task  1/25]  Current/Best:    7.64/  19.13 GFLOPS | Progress: (16/20) | 18.58 s
    [Task  1/25]  Current/Best:    8.52/  19.13 GFLOPS | Progress: (20/20) | 22.04 s Done.
+
    [Task  2/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  2/25]  Current/Best:    5.41/  18.76 GFLOPS | Progress: (4/20) | 3.45 s
    [Task  2/25]  Current/Best:    6.35/  20.06 GFLOPS | Progress: (8/20) | 5.09 s
    [Task  2/25]  Current/Best:   16.43/  20.06 GFLOPS | Progress: (12/20) | 7.17 s
    [Task  2/25]  Current/Best:    5.87/  20.06 GFLOPS | Progress: (16/20) | 8.63 s
    [Task  2/25]  Current/Best:   12.58/  20.06 GFLOPS | Progress: (20/20) | 10.37 s Done.
+
    [Task  3/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  3/25]  Current/Best:   15.68/  15.68 GFLOPS | Progress: (4/20) | 4.28 s
    [Task  3/25]  Current/Best:   13.27/  18.37 GFLOPS | Progress: (8/20) | 7.34 s
    [Task  3/25]  Current/Best:    6.76/  19.40 GFLOPS | Progress: (12/20) | 9.76 s
    [Task  3/25]  Current/Best:   16.47/  23.00 GFLOPS | Progress: (16/20) | 11.86 s
    [Task  3/25]  Current/Best:    6.64/  23.00 GFLOPS | Progress: (20/20) | 14.59 s Done.
+
    [Task  4/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  4/25]  Current/Best:    8.46/  12.11 GFLOPS | Progress: (4/20) | 4.94 s
    [Task  4/25]  Current/Best:   16.94/  18.24 GFLOPS | Progress: (8/20) | 6.90 s
    [Task  4/25]  Current/Best:   12.93/  18.24 GFLOPS | Progress: (12/20) | 10.04 s
    [Task  4/25]  Current/Best:   11.61/  19.87 GFLOPS | Progress: (16/20) | 12.98 s
    [Task  4/25]  Current/Best:   11.00/  19.87 GFLOPS | Progress: (20/20) | 14.87 s Done.
+
    [Task  5/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  5/25]  Current/Best:    3.05/  21.22 GFLOPS | Progress: (4/20) | 3.70 s
    [Task  5/25]  Current/Best:    9.95/  21.22 GFLOPS | Progress: (8/20) | 5.92 s
    [Task  5/25]  Current/Best:   14.24/  21.22 GFLOPS | Progress: (12/20) | 8.44 s
    [Task  5/25]  Current/Best:   17.54/  21.22 GFLOPS | Progress: (16/20) | 10.61 s
    [Task  5/25]  Current/Best:   17.70/  21.22 GFLOPS | Progress: (20/20) | 12.77 s Done.
+
    [Task  6/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  6/25]  Current/Best:    9.43/  13.33 GFLOPS | Progress: (4/20) | 9.03 s
    [Task  6/25]  Current/Best:   17.79/  17.79 GFLOPS | Progress: (8/20) | 11.96 s
    [Task  6/25]  Current/Best:   17.60/  17.79 GFLOPS | Progress: (12/20) | 14.65 s
    [Task  6/25]  Current/Best:   17.73/  17.79 GFLOPS | Progress: (16/20) | 17.19 s
    [Task  6/25]  Current/Best:   15.20/  17.79 GFLOPS | Progress: (20/20) | 21.42 s Done.
+
    [Task  7/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  7/25]  Current/Best:    5.95/  11.25 GFLOPS | Progress: (4/20) | 5.29 s
    [Task  7/25]  Current/Best:   11.27/  11.27 GFLOPS | Progress: (8/20) | 8.57 s
    [Task  7/25]  Current/Best:   14.01/  14.61 GFLOPS | Progress: (12/20) | 11.11 s
    [Task  7/25]  Current/Best:    5.87/  17.73 GFLOPS | Progress: (16/20) | 13.75 s
    [Task  7/25]  Current/Best:   14.99/  19.03 GFLOPS | Progress: (20/20) | 15.92 s Done.
+
    [Task  8/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  8/25]  Current/Best:   16.79/  16.79 GFLOPS | Progress: (4/20) | 4.90 s
    [Task  8/25]  Current/Best:    5.93/  17.00 GFLOPS | Progress: (8/20) | 10.98 s
    [Task  8/25]  Current/Best:   14.53/  21.30 GFLOPS | Progress: (12/20) | 13.75 s
    [Task  8/25]  Current/Best:    6.01/  21.30 GFLOPS | Progress: (16/20) | 23.55 s
    [Task  8/25]  Current/Best:    9.68/  21.30 GFLOPS | Progress: (20/20) | 26.87 s Done.
+
    [Task  9/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  9/25]  Current/Best:   10.16/  19.68 GFLOPS | Progress: (4/20) | 7.93 s
    [Task  9/25]  Current/Best:   15.15/  19.68 GFLOPS | Progress: (8/20) | 10.18 s
    [Task  9/25]  Current/Best:   12.62/  19.68 GFLOPS | Progress: (12/20) | 13.64 s
    [Task  9/25]  Current/Best:   12.22/  19.68 GFLOPS | Progress: (16/20) | 20.07 s
    [Task  9/25]  Current/Best:   19.34/  19.68 GFLOPS | Progress: (20/20) | 21.93 s Done.
+
    [Task 10/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 10/25]  Current/Best:   16.62/  18.08 GFLOPS | Progress: (4/20) | 4.84 s
    [Task 10/25]  Current/Best:   14.00/  18.08 GFLOPS | Progress: (8/20) | 7.48 s
    [Task 10/25]  Current/Best:   21.25/  21.25 GFLOPS | Progress: (12/20) | 9.55 s
    [Task 10/25]  Current/Best:   13.45/  21.25 GFLOPS | Progress: (16/20) | 11.82 s
    [Task 10/25]  Current/Best:   11.19/  21.25 GFLOPS | Progress: (20/20) | 14.12 s Done.
+
    [Task 11/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 11/25]  Current/Best:   11.53/  18.04 GFLOPS | Progress: (4/20) | 4.15 s
    [Task 11/25]  Current/Best:   15.26/  18.04 GFLOPS | Progress: (8/20) | 6.57 s
    [Task 11/25]  Current/Best:   11.73/  19.95 GFLOPS | Progress: (12/20) | 9.03 s
    [Task 11/25]  Current/Best:   17.75/  19.95 GFLOPS | Progress: (16/20) | 11.32 s
    [Task 11/25]  Current/Best:    7.81/  20.24 GFLOPS | Progress: (20/20) | 13.51 s Done.
+
    [Task 12/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 12/25]  Current/Best:   14.96/  18.52 GFLOPS | Progress: (4/20) | 5.28 s
    [Task 12/25]  Current/Best:    6.40/  18.52 GFLOPS | Progress: (8/20) | 7.99 s
    [Task 12/25]  Current/Best:   10.06/  19.63 GFLOPS | Progress: (12/20) | 9.95 s
    [Task 12/25]  Current/Best:   14.26/  19.63 GFLOPS | Progress: (16/20) | 12.67 s
    [Task 12/25]  Current/Best:   14.26/  19.63 GFLOPS | Progress: (20/20) | 18.29 s Done.
+
    [Task 13/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 13/25]  Current/Best:    8.17/  18.73 GFLOPS | Progress: (4/20) | 4.38 s
    [Task 13/25]  Current/Best:   12.13/  18.73 GFLOPS | Progress: (8/20) | 7.13 s
    [Task 13/25]  Current/Best:   12.15/  21.24 GFLOPS | Progress: (12/20) | 9.80 s
    [Task 13/25]  Current/Best:    9.43/  21.24 GFLOPS | Progress: (16/20) | 12.24 s
    [Task 13/25]  Current/Best:   18.23/  21.24 GFLOPS | Progress: (20/20) | 15.92 s Done.
+
    [Task 14/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 14/25]  Current/Best:    6.88/  11.63 GFLOPS | Progress: (4/20) | 4.71 s
    [Task 14/25]  Current/Best:   17.84/  17.84 GFLOPS | Progress: (8/20) | 7.99 s
    [Task 14/25]  Current/Best:   18.97/  18.97 GFLOPS | Progress: (12/20) | 10.63 s
    [Task 14/25]  Current/Best:   11.48/  18.97 GFLOPS | Progress: (16/20) | 12.85 s
    [Task 14/25]  Current/Best:   10.74/  18.97 GFLOPS | Progress: (20/20) | 17.51 s
    [Task 15/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 15/25]  Current/Best:   18.38/  18.38 GFLOPS | Progress: (4/20) | 8.90 s
    [Task 15/25]  Current/Best:   13.06/  18.38 GFLOPS | Progress: (8/20) | 12.97 s
    [Task 15/25]  Current/Best:   12.28/  18.38 GFLOPS | Progress: (12/20) | 14.50 s
    [Task 15/25]  Current/Best:   15.46/  18.38 GFLOPS | Progress: (16/20) | 19.66 s
    [Task 15/25]  Current/Best:   17.83/  19.40 GFLOPS | Progress: (20/2
 0) | 21.24 s
    [Task 16/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 16/25]  Current/Best:   17.69/  17.69 GFLOPS | Progress: (4/20) | 3.42 s Done.
      Done.
-
    [Task 17/25]  Current/Best:   17.71/  21.21 GFLOPS | Progress: (12/20) | 10.90 s
    [Task 17/25]  Current/Best:   12.72/  21.21 GFLOPS | Progress: (16/20) | 13.21 s
    [Task 17/25]  Current/Best:   16.49/  21.21 GFLOPS | Progress: (20/20) | 16.17 s Done.
-
    [Task 18/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 18/25]  Current/Best:   15.02/  17.64 GFLOPS | Progress: (4/20) | 4.05 s
    [Task 18/25]  Current/Best:    6.05/  17.64 GFLOPS | Progress: (8/20) | 14.75 s
    [Task 18/25]  Current/Best:   17.43/  19.72 GFLOPS | Progress: (12/20) | 17.17 s
    [Task 18/25]  Current/Best:    9.34/  19.72 GFLOPS | Progress: (16/20) | 20.29 s
    [Task 18/25]  Current/Best:    9.72/  19.72 GFLOPS | Progress: (20/20) | 25.46 s Done.
-
    [Task 19/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 19/25]  Current/Best:   10.44/  12.15 GFLOPS | Progress: (4/20) | 9.70 s
    [Task 19/25]  Current/Best:    2.69/  16.99 GFLOPS | Progress: (8/20) | 13.18 s
    [Task 19/25]  Current/Best:    6.16/  18.42 GFLOPS | Progress: (12/20) | 16.65 s
    [Task 19/25]  Current/Best:    2.69/  18.42 GFLOPS | Progress: (16/20) | 21.02 s
    [Task 19/25]  Current/Best:    1.55/  22.59 GFLOPS | Progress: (20/20) | 25.77 s Done.
-
    [Task 20/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 20/25]  Current/Best:   15.94/  17.24 GFLOPS | Progress: (4/20) | 4.57 s
    [Task 20/25]  Current/Best:   16.26/  17.24 GFLOPS | Progress: (8/20) | 10.06 s
    [Task 20/25]  Current/Best:   11.49/  17.24 GFLOPS | Progress: (12/20) | 12.50 s
    [Task 20/25]  Current/Best:   17.42/  17.42 GFLOPS | Progress: (16/20) | 15.36 s
    [Task 20/25]  Current/Best:    9.11/  17.42 GFLOPS | Progress: (20/20) | 18.40 s
    [Task 21/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 21/25]  Current/Best:    2.77/  16.67 GFLOPS | Progress: (4/20) | 3.70 s
    [Task 21/25]  Current/Best:    5.29/  18.96 GFLOPS | Progress: (8/20) | 8.05 s
    [Task 21/25]  Current/Best:   17.32/  18.96 GFLOPS | Progress: (12/20) | 10.14 s
    [Task 21/25]  Current/Best:   10.86/  18.96 GFLOPS | Progress: (16/20) | 12.29 s
    [Task 21/25]  Current/Best:   16.04/  18.96 GFLOPS | Progress: (20/2
 0) | 14.19 s
    [Task 22/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
    [Task 16/25]  Current/Best:    6.17/  17.69 GFLOPS | Progress: (8/20) | 5.70 s
    [Task 16/25]  Current/Best:   16.73/  18.02 GFLOPS | Progress: (12/20) | 7.70 s
    [Task 16/25]  Current/Best:    3.98/  20.10 GFLOPS | Progress: (16/20) | 9.54 s
    [Task 16/25]  Current/Best:    9.92/  20.10 GFLOPS | Progress: (20/20) | 12.43 s Done.
+
    [Task 17/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 17/25]  Current/Best:   10.15/  17.82 GFLOPS | Progress: (4/20) | 5.34 s
    [Task 17/25]  Current/Best:   15.32/  17.82 GFLOPS | Progress: (8/20) | 8.23 s
    [Task 17/25]  Current/Best:   11.72/  17.82 GFLOPS | Progress: (12/20) | 13.15 s
    [Task 17/25]  Current/Best:   10.54/  17.82 GFLOPS | Progress: (16/20) | 16.55 s
    [Task 17/25]  Current/Best:   20.72/  23.97 GFLOPS | Progress: (20/20) | 18.68 s Done.
+
    [Task 18/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 18/25]  Current/Best:    6.76/   9.57 GFLOPS | Progress: (4/20) | 7.67 s
    [Task 18/25]  Current/Best:   11.69/  15.64 GFLOPS | Progress: (8/20) | 10.53 s
    [Task 18/25]  Current/Best:   17.27/  19.16 GFLOPS | Progress: (12/20) | 15.37 s
    [Task 18/25]  Current/Best:   10.58/  19.69 GFLOPS | Progress: (16/20) | 18.42 s
    [Task 18/25]  Current/Best:    9.24/  19.69 GFLOPS | Progress: (20/20) | 23.12 s Done.
+
    [Task 19/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 19/25]  Current/Best:    9.79/  14.78 GFLOPS | Progress: (4/20) | 5.02 s
    [Task 19/25]  Current/Best:   10.89/  20.56 GFLOPS | Progress: (8/20) | 9.88 s
    [Task 19/25]  Current/Best:    8.45/  20.56 GFLOPS | Progress: (12/20) | 13.58 s
    [Task 19/25]  Current/Best:   11.27/  20.56 GFLOPS | Progress: (16/20) | 16.23 s
    [Task 19/25]  Current/Best:   10.25/  20.56 GFLOPS | Progress: (20/20) | 20.09 s Done.
+
    [Task 20/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 20/25]  Current/Best:   14.27/  17.93 GFLOPS | Progress: (4/20) | 4.17 s
    [Task 20/25]  Current/Best:    7.42/  18.41 GFLOPS | Progress: (8/20) | 7.95 s
    [Task 20/25]  Current/Best:    7.81/  18.41 GFLOPS | Progress: (12/20) | 10.12 s
    [Task 20/25]  Current/Best:    9.45/  18.41 GFLOPS | Progress: (16/20) | 14.65 s
    [Task 20/25]  Current/Best:    7.88/  18.41 GFLOPS | Progress: (20/20) | 17.96 s
    [Task 21/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 21/25]  Current/Best:   14.31/  17.27 GFLOPS | Progress: (4/20) | 3.35 s
    [Task 21/25]  Current/Best:   13.90/  18.39 GFLOPS | Progress: (8/20) | 6.12 s
    [Task 21/25]  Current/Best:   16.55/  18.39 GFLOPS | Progress: (12/20) | 8.62 s
    [Task 21/25]  Current/Best:   12.48/  18.39 GFLOPS | Progress: (16/20) | 10.60 s
    [Task 21/25]  Current/Best:    7.43/  18.39 GFLOPS | Progress: (20/20)
  | 13.50 s
    [Task 22/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 22/25]  Current/Best:   19.35/  19.35 GFLOPS | Progress: (4/20) | 4.24 s
    [Task 22/25]  Current/Best:   16.57/  19.35 GFLOPS | Progress: (8/20) | 8.80 s
    [Task 22/25]  Current/Best:    6.60/  19.35 GFLOPS | Progress: (12/20) | 10.89 s
    [Task 22/25]  Current/Best:   21.00/  21.00 GFLOPS | Progress: (16/20) | 12.61 s
    [Task 22/25]  Current/Best:    7.65/  21.00 GFLOPS | Progress: (20/20) | 15.21 s Done.
+
    [Task 23/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 23/25]  Current/Best:   10.50/  19.70 GFLOPS | Progress: (4/20) | 5.44 s
    [Task 23/25]  Current/Best:    1.55/  19.88 GFLOPS | Progress: (8/20) | 12.29 s
    [Task 23/25]  Current/Best:    6.52/  19.88 GFLOPS | Progress: (12/20) | 18.45 s
    [Task 23/25]  Current/Best:   18.14/  19.88 GFLOPS | Progress: (16/20) | 21.13 s
    [Task 23/25]  Current/Best:    6.15/  19.88 GFLOPS | Progress: (20/20) | 24.07 s Done.
+
    [Task 24/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 24/25]  Current/Best:    2.44/   7.16 GFLOPS | Progress: (4/20) | 4.94 s
    [Task 24/25]  Current/Best:    3.82/   7.16 GFLOPS | Progress: (8/20) | 11.80 s Done.
      Done.
-
    [Task 22/25]  Current/Best:   10.69/  15.10 GFLOPS | Progress: (4/20) | 5.34 s
    [Task 22/25]  Current/Best:   11.55/  17.98 GFLOPS | Progress: (8/20) | 7.68 s
    [Task 22/25]  Current/Best:    6.82/  17.98 GFLOPS | Progress: (12/20) | 11.65 s
    [Task 22/25]  Current/Best:   10.45/  17.98 GFLOPS | Progress: (16/20) | 13.53 s
    [Task 22/25]  Current/Best:    2.62/  18.14 GFLOPS | Progress: (20/20) | 15.68 s Done.
-
    [Task 23/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 23/25]  Current/Best:   19.05/  19.77 GFLOPS | Progress: (4/20) | 4.12 s
    [Task 23/25]  Current/Best:   18.32/  19.77 GFLOPS | Progress: (8/20) | 7.37 s
    [Task 23/25]  Current/Best:   18.92/  19.77 GFLOPS | Progress: (12/20) | 11.31 s
    [Task 23/25]  Current/Best:    5.23/  19.77 GFLOPS | Progress: (16/20) | 15.25 s
    [Task 23/25]  Current/Best:   17.88/  19.77 GFLOPS | Progress: (20/20) | 20.37 s Done.
-
    [Task 24/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 24/25]  Current/Best:    2.92/   7.98 GFLOPS | Progress: (4/20) | 12.85 s
    [Task 24/25]  Current/Best:    3.00/   8.54 GFLOPS | Progress: (8/20) | 17.42 s
    [Task 24/25]  Current/Best:    2.50/   8.54 GFLOPS | Progress: (12/20) | 28.10 s
    [Task 24/25]  Current/Best:    2.97/   8.54 GFLOPS | Progress: (16/20) | 39.07 s
    [Task 24/25]  Current/Best:    4.63/   8.54 GFLOPS | Progress: (20/20) | 46.11 s
    [Task 25/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
-
    [Task 25/25]  Current/Best:    5.28/   5.28 GFLOPS | Progress: (4/20) | 13.37 s
    [Task 25/25]  Current/Best:    5.77/   5.77 GFLOPS | Progress: (8/20) | 25.27 s
    [Task 25/25]  Current/Best:    5.72/   5.77 GFLOPS | Progress: (12/20) | 27.44 s
    [Task 25/25]  Current/Best:    1.55/   7.85 GFLOPS | Progress: (16/20) | 38.43 s
    [Task 25/25]  Current/Best:    8.06/   8.06 GFLOPS | Progress: (20/20) | 43.15 s
+
    [Task 24/25]  Current/Best:    5.84/   7.16 GFLOPS | Progress: (12/20) | 22.75 s
    [Task 24/25]  Current/Best:    1.89/   7.16 GFLOPS | Progress: (16/20) | 33.71 s
    [Task 24/25]  Current/Best:    5.98/   7.16 GFLOPS | Progress: (20/20) | 44.09 s
    [Task 25/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 25/25]  Current/Best:    5.75/   6.71 GFLOPS | Progress: (4/20) | 4.42 s
    [Task 25/25]  Current/Best:    1.53/   6.71 GFLOPS | Progress: (8/20) | 15.41 s
    [Task 25/25]  Current/Best:    3.04/   9.69 GFLOPS | Progress: (12/20) | 20.57 s
    [Task 25/25]  Current/Best:    6.00/   9.69 GFLOPS | Progress: (16/20) | 31.53 s
    [Task 25/25]  Current/Best:    5.80/   9.69 GFLOPS | Progress: (20/20) | 42.50 s
 
 
 
@@ -665,8 +664,8 @@ Verify that the optimized model runs and produces the same results:
 
  .. code-block:: none
 
-    class='n02123045 tabby, tabby cat' with probability=0.621104
-    class='n02123159 tiger cat' with probability=0.356378
+    class='n02123045 tabby, tabby cat' with probability=0.621102
+    class='n02123159 tiger cat' with probability=0.356380
     class='n02124075 Egyptian cat' with probability=0.019712
     class='n02129604 tiger, Panthera tigris' with probability=0.001215
     class='n04040759 radiator' with probability=0.000262
@@ -723,8 +722,8 @@ improvement in comparing the optimized model to the unoptimized model.
 
  .. code-block:: none
 
-    optimized: {'mean': 415.98896696998054, 'median': 415.9302147499602, 'std': 3.422307767796741}
-    unoptimized: {'mean': 517.6268569099921, 'median': 517.4762197500058, 'std': 2.3963316360720026}
+    optimized: {'mean': 427.6049398500004, 'median': 427.5632347000055, 'std': 1.87073181743225}
+    unoptimized: {'mean': 518.0414347700003, 'median': 518.4623476000013, 'std': 2.0786998699138803}
 
 
 
@@ -747,7 +746,7 @@ profiling/benchmarking.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 12 minutes  14.094 seconds)
+   **Total running time of the script:** ( 12 minutes  0.009 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 95a8504b33..9db270a53b 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -274,7 +274,7 @@ device and returns the measured cost. Network overhead is excluded.
 
  .. code-block:: none
 
-    1.272e-07 secs/op
+    1.469e-07 secs/op
 
 
 
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 6d6bff5b3b..2a459af4a1 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -270,7 +270,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
 
  .. code-block:: none
 
-    [stage(a, placeholder(a, 0x218124c0)), stage(b, placeholder(b, 0x57cd640)), stage(T_add, compute(T_add, body=[a[ax0, ax1, ax2] + b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T.Range(0, 10), "DataPar", ""), T.iter_var(ax2, T.Range(0, 10), "DataPar", "")], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[a[ax0, ax1, ax2] * b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T. [...]
+    [stage(a, placeholder(a, 0x9fb71c0)), stage(b, placeholder(b, 0xe222810)), stage(T_add, compute(T_add, body=[a[ax0, ax1, ax2] + b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T.Range(0, 10), "DataPar", ""), T.iter_var(ax2, T.Range(0, 10), "DataPar", "")], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[a[ax0, ax1, ax2] * b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T.R [...]
 
 
 
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index 3853808b34..cb97321590 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,32 +5,32 @@
 
 Computation times
 =================
-**15:38.310** total execution time for **tutorial** files:
+**15:21.533** total execution time for **tutorial** files:
 
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)                 | 12:14.094 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)                 | 12:00.009 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:14.063 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:14.570 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)     | 01:00.772 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)     | 01:01.082 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)                 | 00:35.961 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)                 | 00:35.831 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)               | 00:31.771 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)               | 00:27.583 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)                               | 00:00.846 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)       | 00:01.446 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)       | 00:00.618 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)                               | 00:00.833 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.184 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.179 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_tutorial_uma.py` (``uma.py``)                                             | 00:00.000 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``)                           | 00:00.000 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``)                             | 00:00.000 | 0.0 MB |
-+------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``)   | 00:00.000 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``)                             | 00:00.000 | 0.0 MB |
++------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_tutorial_install.py` (``install.py``)                                     | 00:00.000 | 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 3f258db573..447f73acea 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -389,7 +389,7 @@ compile and run this new schedule with the parallel operation applied:
 
  .. code-block:: none
 
-    parallel: 0.000007
+    parallel: 0.000008
 
 
 
@@ -498,10 +498,10 @@ We can now compare the different schedules
  .. code-block:: none
 
                 Operator                  Timing             Performance
-                   numpy    7.056659997033421e-06                    1.0
-                   naive              6.7006e-06      0.9495427019038601
-                parallel    6.959200000000001e-06     0.9861889339893957
-                  vector    2.4585599999999997e-05    3.4840278560020805
+                   numpy    7.388540000192734e-06                    1.0
+                   naive    6.653999999999999e-06     0.9005838771701076
+                parallel              8.0759e-06      1.0930305581061124
+                  vector    2.4604200000000004e-05    3.3300489676388287
 
 
 
@@ -922,7 +922,7 @@ matrix multiplication.
 
  .. code-block:: none
 
-    Numpy running time: 0.018855
+    Numpy running time: 0.018827
 
 
 
@@ -980,7 +980,7 @@ optimizations.
 
  .. code-block:: none
 
-    none: 3.346853
+    none: 3.385970
 
 
 
@@ -1080,7 +1080,7 @@ schedule.
 
  .. code-block:: none
 
-    blocking: 0.316665
+    blocking: 0.309784
 
 
 
@@ -1164,7 +1164,7 @@ already cache friendly from our previous optimizations.
 
  .. code-block:: none
 
-    vectorization: 0.360209
+    vectorization: 0.345993
     @I.ir_module
     class Module:
         @T.prim_func
@@ -1230,7 +1230,7 @@ more cache friendly.
 
  .. code-block:: none
 
-    loop permutation: 0.120309
+    loop permutation: 0.122252
     @I.ir_module
     class Module:
         @T.prim_func
@@ -1321,7 +1321,7 @@ optimized schedule.
 
  .. code-block:: none
 
-    array packing: 0.107902
+    array packing: 0.110152
     @I.ir_module
     class Module:
         @T.prim_func
@@ -1404,7 +1404,7 @@ to `C` when all the block results are ready.
 
  .. code-block:: none
 
-    block caching: 0.111348
+    block caching: 0.111498
     @I.ir_module
     class Module:
         @T.prim_func
@@ -1478,7 +1478,7 @@ of thread-level parallelization.
 
  .. code-block:: none
 
-    parallelization: 0.146428
+    parallelization: 0.146479
     @I.ir_module
     class Module:
         @T.prim_func
@@ -1548,13 +1548,13 @@ working, we can compare the results.
  .. code-block:: none
 
                 Operator                  Timing             Performance
-                    none      3.3468527762999996                     1.0
-                blocking     0.31666541800000003     0.09461587920520328
-           vectorization            0.3602094293     0.10762631444404835
-        loop permutation     0.12030926830000002    0.035946985523816165
-           array packing            0.1079019317     0.03223982018691821
-           block caching            0.1113483064    0.033269556159891016
-         parallelization            0.1464283433     0.04375105601802985
+                    none      3.3859701759000003                     1.0
+                blocking            0.3097840192     0.09149047484378935
+           vectorization     0.34599302499999995     0.10218430967367692
+        loop permutation     0.12225169450000002     0.03610536660072772
+           array packing              0.11015217     0.03253193745887654
+           block caching            0.1114983212     0.03292950481182648
+         parallelization            0.1464793376     0.04326066976093946
 
 
 
@@ -1596,7 +1596,7 @@ the computation for specific platforms.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  0.772 seconds)
+   **Total running time of the script:** ( 1 minutes  1.082 seconds)
 
 
 .. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/commit_hash b/docs/commit_hash
index de7c9a8c34..a1598ac56f 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-02e8bbfab66d5b09e3c0a8c789850909a9940a7a
+5d2a94720481ce2e065822229bcd4355c6e3945c
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index d68a73ab5a..984b5d4970 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -585,7 +585,7 @@ class:[&#39;truck 0.9266&#39;] left:471 top:83 right:689 bottom:169
 class:[&#39;bicycle 0.9984&#39;] left:111 top:113 right:577 bottom:447
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  16.314 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  16.641 seconds)</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-darknet-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/7716f96385bd5abb6e822041e285be54/from_darknet.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_darknet.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_keras.html b/docs/how_to/compile_models/from_keras.html
index bb9ebcf6a8..d94f1dbdc4 100644
--- a/docs/how_to/compile_models/from_keras.html
+++ b/docs/how_to/compile_models/from_keras.html
@@ -506,7 +506,7 @@ Tensorflow is also required since it’s used as the default backend of keras.</
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Relay top-1 id: 285, class name: Egyptian cat
 
 1/1 [==============================] - ETA: 0s
-1/1 [==============================] - 1s 938ms/step
+1/1 [==============================] - 1s 969ms/step
 Keras top-1 id: 285, class name: Egyptian cat
 </pre></div>
 </div>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 75cd906fe0..fed9c703ae 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -439,7 +439,7 @@
 <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;x&quot;</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#tuple" title="builtins.tuple" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">x</span><span class="o">.</span><span class="n">shape</span></a><span class="p">)</span>
 </pre></div>
 </div>
-<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip97a8b984-afbf-4461-9c0f-bd955ea40d2d 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.zip731c29af-55b5-40e0-bdf4-c06c42a7a704 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 16408e2b42..d2f72c4d91 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -449,12 +449,13 @@ Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdo
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: &quot;https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip&quot; to /workspace/.oneflow/flowvision_cache/resnet18.zip
 
   0%|          | 0.00/41.5M [00:00&lt;?, ?B/s]
- 19%|#9        | 7.99M/41.5M [00:00&lt;00:00, 61.1MB/s]
- 39%|###8      | 16.0M/41.5M [00:00&lt;00:00, 63.5MB/s]
- 58%|#####7    | 24.0M/41.5M [00:00&lt;00:00, 55.1MB/s]
- 77%|#######7  | 32.0M/41.5M [00:00&lt;00:00, 54.4MB/s]
- 96%|#########5| 39.7M/41.5M [00:00&lt;00:00, 61.5MB/s]
-100%|##########| 41.5M/41.5M [00:00&lt;00:00, 57.1MB/s]
+ 15%|#5        | 6.33M/41.5M [00:00&lt;00:01, 28.2MB/s]
+ 22%|##1       | 9.02M/41.5M [00:00&lt;00:01, 27.3MB/s]
+ 39%|###8      | 16.0M/41.5M [00:00&lt;00:00, 34.9MB/s]
+ 58%|#####7    | 24.0M/41.5M [00:00&lt;00:00, 38.1MB/s]
+ 82%|########2 | 34.1M/41.5M [00:00&lt;00:00, 53.4MB/s]
+ 96%|#########5| 39.7M/41.5M [00:00&lt;00:00, 45.6MB/s]
+100%|##########| 41.5M/41.5M [00:01&lt;00:00, 39.1MB/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 d53afc71f6..73287e3e1b 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -432,10 +432,10 @@ be unstable.</p>
 Downloading: &quot;https://download.pytorch.org/models/resnet18-f37072fd.pth&quot; to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
 
   0%|          | 0.00/44.7M [00:00&lt;?, ?B/s]
- 24%|##3       | 10.6M/44.7M [00:00&lt;00:00, 112MB/s]
- 52%|#####2    | 23.3M/44.7M [00:00&lt;00:00, 124MB/s]
- 79%|#######8  | 35.1M/44.7M [00:00&lt;00:00, 103MB/s]
-100%|##########| 44.7M/44.7M [00:00&lt;00:00, 92.5MB/s]
+ 18%|#7        | 7.99M/44.7M [00:00&lt;00:00, 56.8MB/s]
+ 53%|#####3    | 23.7M/44.7M [00:00&lt;00:00, 107MB/s]
+ 77%|#######7  | 34.6M/44.7M [00:00&lt;00:00, 99.4MB/s]
+100%|##########| 44.7M/44.7M [00:00&lt;00:00, 98.6MB/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 7699ec917a..615b8570df 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -649,7 +649,7 @@ banana (score = 0.00022)
 desk (score = 0.00019)
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  20.940 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  22.270 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 a73022936e..5c130da6d5 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -340,7 +340,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>06:20.263</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>06:23.600</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 81%" />
@@ -349,43 +349,43 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:20.940</p></td>
+<td><p>01:22.270</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
-<td><p>01:16.314</p></td>
+<td><p>01:16.641</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>00:52.277</p></td>
+<td><p>00:53.033</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>00:34.731</p></td>
+<td><p>00:35.979</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>00:30.606</p></td>
+<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>00:30.512</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
-<tr class="row-even"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
-<td><p>00:30.586</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
+<td><p>00:30.511</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
-<td><p>00:27.381</p></td>
+<td><p>00:26.788</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>00:24.781</p></td>
+<td><p>00:24.518</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>00:19.994</p></td>
+<td><p>00:20.686</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>00:02.654</p></td>
+<td><p>00:02.662</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 </tbody>
diff --git a/docs/how_to/deploy_models/deploy_model_on_adreno.html b/docs/how_to/deploy_models/deploy_model_on_adreno.html
index 828aad99a8..77b62115cd 100644
--- a/docs/how_to/deploy_models/deploy_model_on_adreno.html
+++ b/docs/how_to/deploy_models/deploy_model_on_adreno.html
@@ -920,7 +920,7 @@ Top5 predictions:
 Evaluate inference time cost...
 Execution time summary:
  mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)
- 2544.6756    2544.3626    2548.3481    2543.4752      1.3800
+ 2544.5067    2543.8345    2553.5584    2540.0831      3.7938
 </pre></div>
 </div>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-model-on-adreno-py">
diff --git a/docs/how_to/deploy_models/deploy_model_on_android.html b/docs/how_to/deploy_models/deploy_model_on_android.html
index a612bcbb69..99c062d82b 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -662,7 +662,7 @@ to the remote android device.</p>
 Evaluate inference time cost...
 Execution time summary:
  mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)
-  16.7384      16.8832      17.2957      16.0486       0.4502
+  16.4181      16.4232      17.2972      15.8568       0.4876
 </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 e1e6243d3d..eda4883e4e 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -454,23 +454,27 @@ be unstable.</p>
 Downloading: &quot;https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth&quot; to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
 
   0%|          | 0.00/170M [00:00&lt;?, ?B/s]
-  5%|4         | 7.99M/170M [00:00&lt;00:02, 60.6MB/s]
- 14%|#4        | 24.0M/170M [00:00&lt;00:01, 99.4MB/s]
- 20%|#9        | 33.6M/170M [00:00&lt;00:01, 74.2MB/s]
- 27%|##6       | 45.8M/170M [00:00&lt;00:01, 90.0MB/s]
- 33%|###2      | 56.0M/170M [00:00&lt;00:01, 82.1MB/s]
- 38%|###7      | 64.4M/170M [00:00&lt;00:01, 67.4MB/s]
- 44%|####3     | 74.1M/170M [00:01&lt;00:01, 75.1MB/s]
- 48%|####8     | 81.9M/170M [00:01&lt;00:01, 75.6MB/s]
- 54%|#####3    | 91.6M/170M [00:01&lt;00:00, 82.3MB/s]
- 61%|######1   | 104M/170M [00:01&lt;00:00, 85.3MB/s]
- 66%|######6   | 112M/170M [00:01&lt;00:00, 83.7MB/s]
- 72%|#######1  | 122M/170M [00:01&lt;00:00, 86.9MB/s]
- 80%|########  | 136M/170M [00:01&lt;00:00, 96.5MB/s]
- 86%|########5 | 145M/170M [00:01&lt;00:00, 95.3MB/s]
- 91%|######### | 154M/170M [00:01&lt;00:00, 81.6MB/s]
- 96%|#########6| 163M/170M [00:02&lt;00:00, 84.4MB/s]
-100%|##########| 170M/170M [00:02&lt;00:00, 83.1MB/s]
+  5%|4         | 7.99M/170M [00:00&lt;00:02, 66.9MB/s]
+  9%|9         | 16.0M/170M [00:00&lt;00:02, 74.6MB/s]
+ 14%|#4        | 24.0M/170M [00:00&lt;00:02, 74.2MB/s]
+ 18%|#8        | 31.1M/170M [00:00&lt;00:02, 70.0MB/s]
+ 22%|##2       | 37.8M/170M [00:00&lt;00:02, 67.7MB/s]
+ 28%|##8       | 48.0M/170M [00:00&lt;00:01, 68.7MB/s]
+ 33%|###2      | 56.0M/170M [00:00&lt;00:01, 72.3MB/s]
+ 38%|###7      | 64.0M/170M [00:00&lt;00:01, 71.0MB/s]
+ 42%|####2     | 72.0M/170M [00:01&lt;00:01, 72.5MB/s]
+ 47%|####7     | 80.0M/170M [00:01&lt;00:01, 60.4MB/s]
+ 53%|#####2    | 89.8M/170M [00:01&lt;00:01, 70.6MB/s]
+ 58%|#####7    | 98.1M/170M [00:01&lt;00:01, 74.8MB/s]
+ 62%|######2   | 106M/170M [00:01&lt;00:00, 74.9MB/s]
+ 68%|######8   | 116M/170M [00:01&lt;00:00, 84.6MB/s]
+ 73%|#######3  | 125M/170M [00:01&lt;00:00, 79.8MB/s]
+ 78%|#######7  | 132M/170M [00:01&lt;00:00, 76.2MB/s]
+ 82%|########2 | 140M/170M [00:02&lt;00:00, 68.1MB/s]
+ 86%|########6 | 147M/170M [00:02&lt;00:00, 65.4MB/s]
+ 92%|#########1| 156M/170M [00:02&lt;00:00, 73.3MB/s]
+ 98%|#########7| 166M/170M [00:02&lt;00:00, 81.4MB/s]
+100%|##########| 170M/170M [00:02&lt;00:00, 73.5MB/s]
 /venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
   for i in range(dim)
 /venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the &#39;trunc&#39; function NOT &#39;floor&#39;). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode=&#39;trunc&#39;), or for actual floor division, use torch.div(a, b, rounding_mode=& [...]
@@ -568,7 +572,7 @@ 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  34.695 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  31.092 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 99a78f9d04..6ab33561c9 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -495,8 +495,8 @@ training. Other models require a full post training calibration.</p>
 Downloading: &quot;https://download.pytorch.org/models/mobilenet_v2-b0353104.pth&quot; to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
 
   0%|          | 0.00/13.6M [00:00&lt;?, ?B/s]
- 59%|#####8    | 7.99M/13.6M [00:00&lt;00:00, 55.3MB/s]
-100%|##########| 13.6M/13.6M [00:00&lt;00:00, 79.7MB/s]
+ 59%|#####8    | 7.99M/13.6M [00:00&lt;00:00, 70.1MB/s]
+100%|##########| 13.6M/13.6M [00:00&lt;00:00, 81.4MB/s]
 </pre></div>
 </div>
 </div>
@@ -587,7 +587,7 @@ 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)
-  90.3247      90.2764      91.7873      90.1662       0.1911
+  90.3536      90.3023      91.5031      90.1201       0.2210
 </pre></div>
 </div>
 <div class="admonition note">
@@ -626,7 +626,7 @@ 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  14.830 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  13.648 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 4eb8d4731b..2a1b08f83a 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -580,7 +580,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
  mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)
-  120.1595     120.0529     126.2615     118.9527      0.7991
+  121.1705     121.1662     123.4740     120.1414      0.5230
 </pre></div>
 </div>
 <div class="admonition note">
@@ -608,7 +608,7 @@ 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  33.634 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes  36.219 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 2c743970b9..6bacbef0c0 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -521,7 +521,7 @@ for calibration. But the accuracy might be impacted.</p>
   DeprecationWarning,
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  30.337 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  41.224 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 9923205cc7..bc81d4b670 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -463,22 +463,24 @@ to your device.</p>
 Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
 
   0%|          | 0/132723 [00:00&lt;?, ?KB/s]
-  5%|4         | 6533/132723 [00:00&lt;00:01, 65323.37KB/s]
- 11%|#1        | 15050/132723 [00:00&lt;00:01, 76993.85KB/s]
- 17%|#7        | 23021/132723 [00:00&lt;00:01, 78228.80KB/s]
- 24%|##3       | 31465/132723 [00:00&lt;00:01, 80671.20KB/s]
- 30%|###       | 39909/132723 [00:00&lt;00:01, 82026.67KB/s]
- 36%|###6      | 48321/132723 [00:00&lt;00:01, 82734.67KB/s]
- 43%|####2     | 56701/132723 [00:00&lt;00:00, 83079.57KB/s]
- 49%|####9     | 65140/132723 [00:00&lt;00:00, 83494.90KB/s]
- 56%|#####5    | 73750/132723 [00:00&lt;00:00, 84306.36KB/s]
- 62%|######2   | 82303/132723 [00:01&lt;00:00, 84682.87KB/s]
- 68%|######8   | 90772/132723 [00:01&lt;00:00, 84670.56KB/s]
- 75%|#######4  | 99312/132723 [00:01&lt;00:00, 84890.79KB/s]
- 81%|########1 | 107929/132723 [00:01&lt;00:00, 85275.76KB/s]
- 88%|########7 | 116517/132723 [00:01&lt;00:00, 85454.83KB/s]
- 94%|#########4| 125108/132723 [00:01&lt;00:00, 85589.40KB/s]
-100%|##########| 132723/132723 [00:01&lt;00:00, 83416.58KB/s]
+  4%|4         | 5549/132723 [00:00&lt;00:02, 55480.00KB/s]
+ 10%|#         | 13530/132723 [00:00&lt;00:01, 69783.99KB/s]
+ 16%|#6        | 21504/132723 [00:00&lt;00:01, 74325.52KB/s]
+ 22%|##2       | 29558/132723 [00:00&lt;00:01, 76773.10KB/s]
+ 28%|##8       | 37599/132723 [00:00&lt;00:01, 78083.21KB/s]
+ 34%|###4      | 45505/132723 [00:00&lt;00:01, 78410.93KB/s]
+ 40%|####      | 53347/132723 [00:00&lt;00:01, 78295.48KB/s]
+ 46%|####6     | 61177/132723 [00:00&lt;00:00, 77924.61KB/s]
+ 52%|#####1    | 68970/132723 [00:00&lt;00:00, 77763.46KB/s]
+ 58%|#####7    | 76747/132723 [00:01&lt;00:00, 77761.05KB/s]
+ 64%|######3   | 84524/132723 [00:01&lt;00:00, 77584.37KB/s]
+ 70%|######9   | 92283/132723 [00:01&lt;00:00, 77531.59KB/s]
+ 75%|#######5  | 100037/132723 [00:01&lt;00:00, 77315.25KB/s]
+ 81%|########1 | 107769/132723 [00:01&lt;00:00, 77253.54KB/s]
+ 87%|########7 | 115496/132723 [00:01&lt;00:00, 77251.20KB/s]
+ 93%|#########2| 123222/132723 [00:01&lt;00:00, 77190.27KB/s]
+ 99%|#########8| 130984/132723 [00:01&lt;00:00, 77315.01KB/s]
+100%|##########| 132723/132723 [00:01&lt;00:00, 76846.23KB/s]
 </pre></div>
 </div>
 <p>Create TVM runtime and do inference
@@ -517,7 +519,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
 <span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
 </pre></div>
 </div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  35.246 seconds)</p>
+<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  31.591 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 159b9fc4f8..fc90c6c3da 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -340,7 +340,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>14:59.337</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>15:03.595</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 86%" />
@@ -349,39 +349,39 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>03:35.246</p></td>
+<td><p>03:31.591</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><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>03:34.695</p></td>
+<td><p>03:31.092</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>02:33.634</p></td>
+<td><p>02:36.219</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="deploy_quantized.html#sphx-glr-how-to-deploy-models-deploy-quantized-py"><span class="std std-ref">Deploy a Quantized Model on Cuda</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_quantized.py</span></code>)</p></td>
-<td><p>01:30.337</p></td>
+<td><p>01:41.224</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>01:14.830</p></td>
+<td><p>01:13.648</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_adreno.html#sphx-glr-how-to-deploy-models-deploy-model-on-adreno-py"><span class="std std-ref">Deploy the Pretrained Model on Adreno</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_adreno.py</span></code>)</p></td>
-<td><p>00:53.947</p></td>
+<td><p>00:53.778</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:41.053</p></td>
+<td><p>00:40.505</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_nano.html#sphx-glr-how-to-deploy-models-deploy-model-on-nano-py"><span class="std std-ref">Deploy the Pretrained Model on Jetson Nano</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_nano.py</span></code>)</p></td>
-<td><p>00:27.894</p></td>
+<td><p>00:27.912</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:27.696</p></td>
+<td><p>00:27.620</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index 4b77f955bb..0419856197 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -619,7 +619,7 @@ 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.zip52f2036a-8984-480b-83dd-d014682074bc 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.zip97a75cf9-e103-4d80-9a8b-55a928cdb2c5 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 7ffa8b9886..1496e8019c 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -340,7 +340,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:54.468</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:52.960</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 84%" />
@@ -349,15 +349,15 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:50.607</p></td>
+<td><p>00:49.149</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>00:02.746</p></td>
+<td><p>00:02.714</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="use_pass_infra.html#sphx-glr-how-to-extend-tvm-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></td>
-<td><p>00:01.108</p></td>
+<td><p>00:01.090</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index a76facc54d..cae8c854ce 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -526,10 +526,10 @@ profile the execution time of each passes.</p>
 </pre></div>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 18360us [18360us] (48.36%; 48.36%)
-FoldScaleAxis: 19607us [10us] (51.64%; 51.64%)
-        FoldConstant: 19597us [1711us] (51.62%; 99.95%)
-                InferType: 17886us [17886us] (47.11%; 91.27%)
+InferType: 18184us [18184us] (48.43%; 48.43%)
+FoldScaleAxis: 19362us [8us] (51.57%; 51.57%)
+        FoldConstant: 19354us [1790us] (51.55%; 99.96%)
+                InferType: 17564us [17564us] (46.78%; 90.75%)
 </pre></div>
 </div>
 </div>
@@ -551,10 +551,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
 </pre></div>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 17882us [17882us] (48.27%; 48.27%)
-FoldScaleAxis: 19168us [7us] (51.73%; 51.73%)
-        FoldConstant: 19161us [1728us] (51.72%; 99.96%)
-                InferType: 17433us [17433us] (47.05%; 90.98%)
+InferType: 17828us [17828us] (47.89%; 47.89%)
+FoldScaleAxis: 19403us [7us] (52.11%; 52.11%)
+        FoldConstant: 19396us [1734us] (52.10%; 99.96%)
+                InferType: 17662us [17662us] (47.44%; 91.06%)
 </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 a090a330ef..045eab52c0 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -575,7 +575,7 @@ 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: 36.574817 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 35.153598 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 21e319668c..d640dfdf02 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -867,7 +867,7 @@ be able to run on our build server</p>
     <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms&quot;</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 13.187625 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 11.614768 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 a49d1895ed..9bfbc76bcc 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -472,8 +472,8 @@ 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: 0.019611
-Baseline: 3.458809
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019183
+Baseline: 3.476481
 </pre></div>
 </div>
 <p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -532,7 +532,7 @@ 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: 0.327382
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.314903
 </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: 0.346190
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.346718
 </pre></div>
 </div>
 <p>Here is the generated IR after vectorization.</p>
@@ -644,7 +644,7 @@ 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: 0.131481
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.122469
 </pre></div>
 </div>
 <p>Here is the generated IR after loop permutation.</p>
@@ -721,7 +721,7 @@ 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: 0.110400
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109833
 </pre></div>
 </div>
 <p>Here is the generated IR after array packing.</p>
@@ -799,7 +799,7 @@ 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: 0.113464
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111797
 </pre></div>
 </div>
 <p>Here is the generated IR after blocking.</p>
@@ -879,7 +879,7 @@ class Module:
 <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: 0.148611
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.147873
 </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 619ba3d2b6..8ebbdb2bea 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -340,7 +340,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:36.018</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:35.639</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 83%" />
@@ -349,15 +349,15 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:33.366</p></td>
+<td><p>00:33.027</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>00:01.535</p></td>
+<td><p>00:01.539</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="opt_conv_cuda.html#sphx-glr-how-to-optimize-operators-opt-conv-cuda-py"><span class="std std-ref">How to optimize convolution on GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_cuda.py</span></code>)</p></td>
-<td><p>00:01.117</p></td>
+<td><p>00:01.073</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 f005b3952b..fd53ea51cc 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -340,7 +340,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>09:19.252</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>09:15.990</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 85%" />
@@ -349,27 +349,27 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></td>
-<td><p>05:35.577</p></td>
+<td><p>05:36.234</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>01:40.746</p></td>
+<td><p>01:39.092</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="tune_network_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></td>
-<td><p>01:06.985</p></td>
+<td><p>01:06.080</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="tune_sparse_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-sparse-x86-py"><span class="std std-ref">Auto-scheduling Sparse Matrix Multiplication on CPU with Custom Sketch Rule</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_sparse_x86.py</span></code>)</p></td>
-<td><p>00:28.559</p></td>
+<td><p>00:27.820</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></td>
-<td><p>00:14.183</p></td>
+<td><p>00:13.907</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></td>
-<td><p>00:13.202</p></td>
+<td><p>00:12.857</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 e00a8b8e8c..56d7a9534e 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
@@ -507,12 +507,12 @@ class Module:
         bias_1 = T.match_buffer(bias, (1, 512, 1, 1))
         compute_1 = T.match_buffer(compute, (1, 512, 7, 7))
         blockIdx_x = T.env_thread(&quot;blockIdx.x&quot;)
-        T.launch_thread(blockIdx_x, 64)
+        T.launch_thread(blockIdx_x, 32)
         conv2d_nchw = T.allocate([8], &quot;float32&quot;, &quot;local&quot;)
         pad_temp_shared = T.allocate([252], &quot;float32&quot;, &quot;shared&quot;)
-        kernel_shared = T.allocate([96], &quot;float32&quot;, &quot;shared&quot;)
+        kernel_shared = T.allocate([192], &quot;float32&quot;, &quot;shared&quot;)
         threadIdx_x = T.env_thread(&quot;threadIdx.x&quot;)
-        T.launch_thread(threadIdx_x, 49)
+        T.launch_thread(threadIdx_x, 98)
         conv2d_nchw_1 = T.buffer_decl((8,), data=conv2d_nchw, scope=&quot;local&quot;, align=32)
         conv2d_nchw_1[0] = T.float32(0)
         conv2d_nchw_1[1] = T.float32(0)
@@ -522,42 +522,342 @@ class Module:
         conv2d_nchw_1[5] = T.float32(0)
         conv2d_nchw_1[6] = T.float32(0)
         conv2d_nchw_1[7] = T.float32(0)
-        for rc_outer_outer, rx_outer_outer in T.grid(128, 3):
+        for rc_outer_outer in range(128):
             cse_var_1: T.int32 = rc_outer_outer * 196
             threadIdx_x_1 = T.env_thread(&quot;threadIdx.x&quot;)
             pad_temp_shared_1 = T.buffer_decl((252,), data=pad_temp_shared, scope=&quot;shared&quot;)
             data_2 = T.buffer_decl((25088,), data=data_1.data)
-            with T.launch_thread(threadIdx_x_1, 49):
-                pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(7 &lt;= threadIdx_x_1 and 1 &lt;= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 &lt; 8, data_2[cse_var_1 + threadIdx_x_1 + rx_outer_outer - 8], T.float32(0))
-            with T.launch_thread(threadIdx_x_1, 49):
-                pad_temp_shared_1[threadIdx_x_1 + 49] = T.if_then_else(1 &lt;= (threadIdx_x_1 // 7 + 7) % 9 and (threadIdx_x_1 // 7 + 7) % 9 &lt; 8 and 1 &lt;= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 &lt; 8, data_2[cse_var_1 + (threadIdx_x_1 + 49) // 63 * 49 + (threadIdx_x_1 // 7 + 7) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
-            with T.launch_thread(threadIdx_x_1, 49):
-                pad_temp_shared_1[threadIdx_x_1 + 98] = T.if_then_else(1 &lt;= (threadIdx_x_1 // 7 + 5) % 9 and (threadIdx_x_1 // 7 + 5) % 9 &lt; 8 and 1 &lt;= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 &lt; 8, data_2[cse_var_1 + (threadIdx_x_1 + 98) // 63 * 49 + (threadIdx_x_1 // 7 + 5) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
-            with T.launch_thread(threadIdx_x_1, 49):
-                pad_temp_shared_1[threadIdx_x_1 + 147] = T.if_then_else(1 &lt;= (threadIdx_x_1 // 7 + 3) % 9 and (threadIdx_x_1 // 7 + 3) % 9 &lt; 8 and 1 &lt;= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 &lt; 8, data_2[cse_var_1 + (threadIdx_x_1 + 147) // 63 * 49 + (threadIdx_x_1 // 7 + 3) % 9 * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
-            with T.launch_thread(threadIdx_x_1, 49):
-                pad_temp_shared_1[threadIdx_x_1 + 196] = T.if_then_else(1 &lt;= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 &lt; 8, data_2[cse_var_1 + (threadIdx_x_1 + 196) // 63 * 49 + (threadIdx_x_1 // 7 + 1) * 7 + rx_outer_outer + threadIdx_x_1 % 7 - 8], T.float32(0))
-            with T.launch_thread(threadIdx_x_1, 49):
-                if T.likely(threadIdx_x_1 &lt; 7):
-                    pad_temp_shared_1[threadIdx_x_1 + 245] = T.float32(0)
+            with T.launch_thread(threadIdx_x_1, 98):
+                pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(9 &lt;= threadIdx_x_1 % 63 and 1 &lt;= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 &lt; 8, data_2[cse_var_1 + threadIdx_x_1 // 9 * 7 + threadIdx_x_1 % 9 - 8], T.float32(0))
+            with T.launch_thread(threadIdx_x_1, 98):
+                pad_temp_shared_1[threadIdx_x_1 + 98] = T.if_then_else(9 &lt;= (threadIdx_x_1 + 35) % 63 and 1 &lt;= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 &lt; 8, data_2[cse_var_1 + (threadIdx_x_1 + 98) // 9 * 7 + (threadIdx_x_1 + 8) % 9 - 8], T.float32(0))
+            with T.launch_thread(threadIdx_x_1, 98):
+                if T.likely(threadIdx_x_1 &lt; 56):
+                    pad_temp_shared_1[threadIdx_x_1 + 196] = T.if_then_else(9 &lt;= (threadIdx_x_1 + 7) % 63 and 1 &lt;= (threadIdx_x_1 + 7) % 9 and (threadIdx_x_1 + 7) % 9 &lt; 8, data_2[cse_var_1 + (threadIdx_x_1 + 196) // 9 * 7 + (threadIdx_x_1 + 7) % 9 - 8], T.float32(0))
             threadIdx_x_2 = T.env_thread(&quot;threadIdx.x&quot;)
-            kernel_shared_1 = T.buffer_decl((96,), data=kernel_shared, scope=&quot;shared&quot;)
+            kernel_shared_1 = T.buffer_decl((192,), data=kernel_shared, scope=&quot;shared&quot;)
             kernel_2 = T.buffer_decl((2359296,), data=kernel_1.data)
-            with T.launch_thread(threadIdx_x_2, 49):
-                kernel_shared_1[threadIdx_x_2] = kernel_2[blockIdx_x * 36864 + threadIdx_x_2 // 12 * 4608 + rc_outer_outer * 36 + threadIdx_x_2 % 12 * 3 + rx_outer_outer]
-            with T.launch_thread(threadIdx_x_2, 49):
-                if T.likely(threadIdx_x_2 &lt; 47):
-                    kernel_shared_1[threadIdx_x_2 + 49] = kernel_2[blockIdx_x * 36864 + (threadIdx_x_2 + 49) // 12 * 4608 + rc_outer_outer * 36 + (threadIdx_x_2 + 1) % 12 * 3 + rx_outer_outer]
-            for ry_outer_inner, ff_outer_inner in T.grid(3, 8):
-                cse_var_2: T.int32 = ff_outer_inner * 12 + ry_outer_inner
-                conv2d_nchw_1[ff_outer_inner] = conv2d_nchw_1[ff_outer_inner] + pad_temp_shared_1[ry_outer_inner * 7 + threadIdx_x] * kernel_shared_1[cse_var_2]
-                conv2d_nchw_1[ff_outer_inner] = conv2d_nchw_1[ff_outer_inner] + pad_temp_shared_1[ry_outer_inner * 7 + threadIdx_x + 63] * kernel_shared_1[cse_var_2 + 3]
-                conv2d_nchw_1[ff_outer_inner] = conv2d_nchw_1[ff_outer_inner] + pad_temp_shared_1[ry_outer_inner * 7 + threadIdx_x + 126] * kernel_shared_1[cse_var_2 + 6]
-                conv2d_nchw_1[ff_outer_inner] = conv2d_nchw_1[ff_outer_inner] + pad_temp_shared_1[ry_outer_inner * 7 + threadIdx_x + 189] * kernel_shared_1[cse_var_2 + 9]
+            with T.launch_thread(threadIdx_x_2, 98):
+                kernel_shared_1[threadIdx_x_2] = kernel_2[blockIdx_x * 73728 + threadIdx_x_2 // 12 * 4608 + rc_outer_outer * 36 + threadIdx_x_2 % 12 // 3 * 9 + threadIdx_x_2 % 3]
+            with T.launch_thread(threadIdx_x_2, 98):
+                if T.likely(threadIdx_x_2 &lt; 94):
+                    kernel_shared_1[threadIdx_x_2 + 98] = kernel_2[blockIdx_x * 73728 + (threadIdx_x_2 + 98) // 12 * 4608 + rc_outer_outer * 36 + (threadIdx_x_2 + 2) % 12 // 3 * 9 + (threadIdx_x_2 + 2) % 3]
+            conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96]
+            conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96 + 12]
+            conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 1]
+            conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 13]
+            conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 2]
+            conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 14]
+            conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96 + 24]
+            conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96 + 36]
+            conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 25]
+            conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 37]
+            conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 26]
+            conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 38]
+            conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96 + 48]
+            conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96 + 60]
+            conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 49]
+            conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 61]
+            conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 50]
+            conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 62]
+            conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96 + 72]
+            conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96 + 84]
+            conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 73]
+            conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 85]
+            conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 74]
+            conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 86]
+            conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 3]
+            conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 15]
+            conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 4]
+            conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 16]
+            conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 5]
+            conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 17]
+            conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 27]
+            conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 39]
+            conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 28]
+            conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 40]
+            conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 29]
+            conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 41]
+            conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 51]
+            conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 63]
+            conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 52]
+            conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 64]
+            conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 53]
+            conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 65]
+            conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 75]
+            conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 87]
+            conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 76]
+            conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 88]
+            conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 77]
+            conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 89]
+            conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 6]
+            conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 18]
+            conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 7]
+            conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 19]
+            conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 8]
+            conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 20]
+            conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 30]
+            conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 42]
+            conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 31]
+            conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 43]
+            conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 32]
+            conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 44]
+            conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 54]
+            conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 66]
+            conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 55]
+            conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 67]
+            conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 56]
+            conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 68]
+            conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 78]
+            conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 90]
+            conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 79]
+            conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 91]
+            conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 80]
+            conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 92]
+            conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 9]
+            conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 21]
+            conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 10]
+            conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 22]
+            conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 11]
+            conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 23]
+            conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 33]
+            conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 45]
+            conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 34]
+            conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 46]
+            conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 35]
+            conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 47]
+            conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 57]
+            conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 69]
+            conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 58]
+            conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 70]
+            conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 59]
+            conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 71]
+            conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 81]
+            conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 93]
+            conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 82]
+            conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 94]
+            conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 83]
+            conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 95]
+            with T.launch_thread(threadIdx_x_1, 98):
+                pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(1 &lt;= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 &lt; 8, data_2[cse_var_1 + threadIdx_x_1 // 9 * 7 + threadIdx_x_1 % 9 - 1], T.float32(0))
+            with T.launch_thread(threadIdx_x_1, 98):
+                pad_temp_shared_1[threadIdx_x_1 + 98] = T.if_then_else(1 &lt;= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 &lt; 8, data_2[cse_var_1 + (threadIdx_x_1 + 98) // 9 * 7 + (threadIdx_x_1 + 8) % 9 - 1], T.float32(0))
+            with T.launch_thread(threadIdx_x_1, 98):
+                if T.likely(threadIdx_x_1 &lt; 56):
+                    pad_temp_shared_1[threadIdx_x_1 + 196] = T.if_then_else(1 &lt;= (threadIdx_x_1 + 7) % 9 and (threadIdx_x_1 + 7) % 9 &lt; 8, data_2[cse_var_1 + (threadIdx_x_1 + 196) // 9 * 7 + (threadIdx_x_1 + 7) % 9 - 1], T.float32(0))
+            with T.launch_thread(threadIdx_x_2, 98):
+                kernel_shared_1[threadIdx_x_2] = kernel_2[blockIdx_x * 73728 + threadIdx_x_2 // 12 * 4608 + rc_outer_outer * 36 + threadIdx_x_2 % 12 // 3 * 9 + threadIdx_x_2 % 3 + 3]
+            with T.launch_thread(threadIdx_x_2, 98):
+                if T.likely(threadIdx_x_2 &lt; 94):
+                    kernel_shared_1[threadIdx_x_2 + 98] = kernel_2[blockIdx_x * 73728 + (threadIdx_x_2 + 98) // 12 * 4608 + rc_outer_outer * 36 + (threadIdx_x_2 + 2) % 12 // 3 * 9 + (threadIdx_x_2 + 2) % 3 + 3]
+            conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96]
+            conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96 + 12]
+            conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 1]
+            conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 13]
+            conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 2]
+            conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 14]
+            conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96 + 24]
+            conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96 + 36]
+            conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 25]
+            conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 37]
+            conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 26]
+            conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 38]
+            conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96 + 48]
+            conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96 + 60]
+            conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 49]
+            conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 61]
+            conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 50]
+            conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 62]
+            conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96 + 72]
+            conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96 + 84]
+            conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 73]
+            conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 85]
+            conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 74]
+            conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 86]
+            conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 3]
+            conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 15]
+            conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 4]
+            conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 16]
+            conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 5]
+            conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 17]
+            conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 27]
+            conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 39]
+            conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 28]
+            conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 40]
+            conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 29]
+            conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 41]
+            conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 51]
+            conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 63]
+            conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 52]
+            conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 64]
+            conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 53]
+            conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 65]
+            conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 75]
+            conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 87]
+            conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 76]
+            conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 88]
+            conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 77]
+            conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 89]
+            conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 6]
+            conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 18]
+            conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 7]
+            conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 19]
+            conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 8]
+            conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 20]
+            conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 30]
+            conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 42]
+            conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 31]
+            conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 43]
+            conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 32]
+            conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 44]
+            conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 54]
+            conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 66]
+            conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 55]
+            conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 67]
+            conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 56]
+            conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 68]
+            conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 78]
+            conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 90]
+            conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 79]
+            conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 91]
+            conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 80]
+            conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 92]
+            conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 9]
+            conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 21]
+            conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 10]
+            conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 22]
+            conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 11]
+            conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 23]
+            conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 33]
+            conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 45]
+            conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 34]
+            conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 46]
+            conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 35]
+            conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 47]
+            conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 57]
+            conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 69]
+            conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 58]
+            conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 70]
+            conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 59]
+            conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 71]
+            conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 81]
+            conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 93]
+            conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 82]
+            conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 94]
+            conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 83]
+            conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 95]
+            with T.launch_thread(threadIdx_x_1, 98):
+                pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(threadIdx_x_1 % 63 &lt; 54 and 1 &lt;= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 &lt; 8, data_2[cse_var_1 + threadIdx_x_1 // 9 * 7 + threadIdx_x_1 % 9 + 6], T.float32(0))
+            with T.launch_thread(threadIdx_x_1, 98):
+                pad_temp_shared_1[threadIdx_x_1 + 98] = T.if_then_else((threadIdx_x_1 + 35) % 63 &lt; 54 and 1 &lt;= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 &lt; 8, data_2[cse_var_1 + (threadIdx_x_1 + 98) // 9 * 7 + (threadIdx_x_1 + 8) % 9 + 6], T.float32(0))
+            with T.launch_thread(threadIdx_x_1, 98):
+                if T.likely(threadIdx_x_1 &lt; 56):
+                    pad_temp_shared_1[threadIdx_x_1 + 196] = T.if_then_else((threadIdx_x_1 + 7) % 63 &lt; 54 and 1 &lt;= (threadIdx_x_1 + 7) % 9 and (threadIdx_x_1 + 7) % 9 &lt; 8, data_2[cse_var_1 + (threadIdx_x_1 + 196) // 9 * 7 + (threadIdx_x_1 + 7) % 9 + 6], T.float32(0))
+            with T.launch_thread(threadIdx_x_2, 98):
+                kernel_shared_1[threadIdx_x_2] = kernel_2[blockIdx_x * 73728 + threadIdx_x_2 // 12 * 4608 + rc_outer_outer * 36 + threadIdx_x_2 % 12 // 3 * 9 + threadIdx_x_2 % 3 + 6]
+            with T.launch_thread(threadIdx_x_2, 98):
+                if T.likely(threadIdx_x_2 &lt; 94):
+                    kernel_shared_1[threadIdx_x_2 + 98] = kernel_2[blockIdx_x * 73728 + (threadIdx_x_2 + 98) // 12 * 4608 + rc_outer_outer * 36 + (threadIdx_x_2 + 2) % 12 // 3 * 9 + (threadIdx_x_2 + 2) % 3 + 6]
+            conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96]
+            conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96 + 12]
+            conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 1]
+            conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 13]
+            conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 2]
+            conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 14]
+            conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96 + 24]
+            conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96 + 36]
+            conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 25]
+            conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 37]
+            conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 26]
+            conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 38]
+            conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96 + 48]
+            conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96 + 60]
+            conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 49]
+            conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 61]
+            conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 50]
+            conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 62]
+            conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96 + 72]
+            conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 96 + 84]
+            conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 73]
+            conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 96 + 85]
+            conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 74]
+            conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 96 + 86]
+            conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 3]
+            conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 15]
+            conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 4]
+            conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 16]
+            conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 5]
+            conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 17]
+            conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 27]
+            conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 39]
+            conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 28]
+            conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 40]
+            conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 29]
+            conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 41]
+            conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 51]
+            conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 63]
+            conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 52]
+            conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 64]
+            conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 53]
+            conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 65]
+            conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 75]
+            conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 96 + 87]
+            conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 76]
+            conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 96 + 88]
+            conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 77]
+            conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 96 + 89]
+            conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 6]
+            conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 18]
+            conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 7]
+            conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 19]
+            conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 8]
+            conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 20]
+            conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 30]
+            conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 42]
+            conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 31]
+            conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 43]
+            conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 32]
+            conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 44]
+            conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 54]
+            conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 66]
+            conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 55]
+            conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 67]
+            conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 56]
+            conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 68]
+            conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 78]
+            conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 96 + 90]
+            conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 79]
+            conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 96 + 91]
+            conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 80]
+            conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 96 + 92]
+            conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 9]
+            conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 21]
+            conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 10]
+            conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 22]
+            conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 11]
+            conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 23]
+            conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 33]
+            conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 45]
+            conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 34]
+            conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 46]
+            conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 35]
+            conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 47]
+            conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 57]
+            conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 69]
+            conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 58]
+            conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 70]
+            conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 59]
+            conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 71]
+            conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 81]
+            conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 96 + 93]
+            conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 82]
+            conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 96 + 94]
+            conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 83]
+            conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 96 + 95]
         for i1_inner in range(8):
             compute_2 = T.buffer_decl((25088,), data=compute_1.data)
             bias_2 = T.buffer_decl((512,), data=bias_1.data)
-            compute_2[blockIdx_x * 392 + i1_inner * 49 + threadIdx_x] = T.max(conv2d_nchw_1[i1_inner] + bias_2[blockIdx_x * 8 + i1_inner], T.float32(0))
+            compute_2[blockIdx_x * 784 + threadIdx_x // 49 * 392 + i1_inner * 49 + threadIdx_x % 49] = T.max(conv2d_nchw_1[i1_inner] + bias_2[blockIdx_x * 16 + threadIdx_x // 49 * 8 + i1_inner], T.float32(0))
 </pre></div>
 </div>
 </div>
@@ -591,7 +891,7 @@ class Module:
 <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: 0.334 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.319 ms
 </pre></div>
 </div>
 </div>
@@ -620,9 +920,9 @@ conv2d_nchw_nn_o_i, conv2d_nchw_nn_i = s[conv2d_nchw].split(conv2d_nchw_nn, fact
 conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
 conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
 conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
-conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
-conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=8)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=1)
+conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
+conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=4)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=2)
 conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
 conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
 conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
@@ -632,18 +932,18 @@ conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, fact
 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=4)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=1)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
 conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
-conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
-conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
+conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
+conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
 conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
 s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
 compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
 compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
 compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
 compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=8)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=1)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=2)
 compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
 compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
 compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
@@ -669,14 +969,14 @@ 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=49)
+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=98)
 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=49)
+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=98)
 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;, 16)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, &quot;auto_unroll_max_step&quot;, 1024)
 s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, &quot;unroll_explicit&quot;, True)
 
 CUDA source code:
@@ -694,10 +994,10 @@ CUDA source code:
   #define int64_t long long
   #define uint64_t unsigned long long
 #endif
-extern &quot;C&quot; __global__ void __launch_bounds__(49) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+extern &quot;C&quot; __global__ void __launch_bounds__(98) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
   float conv2d_nchw[8];
   __shared__ float pad_temp_shared[252];
-  __shared__ float kernel_shared[96];
+  __shared__ float kernel_shared[192];
   conv2d_nchw[0] = 0.000000e+00f;
   conv2d_nchw[1] = 0.000000e+00f;
   conv2d_nchw[2] = 0.000000e+00f;
@@ -707,33 +1007,330 @@ extern &quot;C&quot; __global__ void __launch_bounds__(49) default_function_kern
   conv2d_nchw[6] = 0.000000e+00f;
   conv2d_nchw[7] = 0.000000e+00f;
   for (int rc_outer_outer = 0; rc_outer_outer &lt; 128; ++rc_outer_outer) {
-    for (int rx_outer_outer = 0; rx_outer_outer &lt; 3; ++rx_outer_outer) {
-      __syncthreads();
-      pad_temp_shared[((int)threadIdx.x)] = ((((7 &lt;= ((int)threadIdx.x)) &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 * 196) + ((int)threadIdx.x)) + rx_outer_outer) - 8)] : 0.000000e+00f);
-      pad_temp_shared[(((int)threadIdx.x) + 49)] = (((((1 &lt;= (((((int)threadIdx.x) / 7) + 7) % 9)) &amp;&amp; ((((((int)threadIdx.x) / 7) + 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 * 196) + (((((int)threadIdx.x) + 49) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
-      pad_temp_shared[(((int)threadIdx.x) + 98)] = (((((1 &lt;= (((((int)threadIdx.x) / 7) + 5) % 9)) &amp;&amp; ((((((int)threadIdx.x) / 7) + 5) % 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 * 196) + (((((int)threadIdx.x) + 98) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
-      pad_temp_shared[(((int)threadIdx.x) + 147)] = (((((1 &lt;= (((((int)threadIdx.x) / 7) + 3) % 9)) &amp;&amp; ((((((int)threadIdx.x) / 7) + 3) % 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 * 196) + (((((int)threadIdx.x) + 147) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
-      pad_temp_shared[(((int)threadIdx.x) + 196)] = (((1 &lt;= (rx_outer_outer + (((int)threadIdx.x) % 7))) &amp;&amp; ((rx_outer_outer + (((int)threadIdx.x) % 7)) &lt; 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 196) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
-      if (((int)threadIdx.x) &lt; 7) {
-        pad_temp_shared[(((int)threadIdx.x) + 245)] = 0.000000e+00f;
-      }
-      kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) % 12) * 3)) + rx_outer_outer)];
-      if (((int)threadIdx.x) &lt; 47) {
-        kernel_shared[(((int)threadIdx.x) + 49)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 49) / 12) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 1) % 12) * 3)) + rx_outer_outer)];
-      }
-      __syncthreads();
-      for (int ry_outer_inner = 0; ry_outer_inner &lt; 3; ++ry_outer_inner) {
-        for (int ff_outer_inner = 0; ff_outer_inner &lt; 8; ++ff_outer_inner) {
-          conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[((ry_outer_inner * 7) + ((int)threadIdx.x))] * kernel_shared[((ff_outer_inner * 12) + ry_outer_inner)]));
-          conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((ry_outer_inner * 7) + ((int)threadIdx.x)) + 63)] * kernel_shared[(((ff_outer_inner * 12) + ry_outer_inner) + 3)]));
-          conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((ry_outer_inner * 7) + ((int)threadIdx.x)) + 126)] * kernel_shared[(((ff_outer_inner * 12) + ry_outer_inner) + 6)]));
-          conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((ry_outer_inner * 7) + ((int)threadIdx.x)) + 189)] * kernel_shared[(((ff_outer_inner * 12) + ry_outer_inner) + 9)]));
-        }
-      }
+    __syncthreads();
+    pad_temp_shared[((int)threadIdx.x)] = ((((9 &lt;= (((int)threadIdx.x) % 63)) &amp;&amp; (1 &lt;= (((int)threadIdx.x) % 9))) &amp;&amp; ((((int)threadIdx.x) % 9) &lt; 8)) ? data[((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+    pad_temp_shared[(((int)threadIdx.x) + 98)] = ((((9 &lt;= ((((int)threadIdx.x) + 35) % 63)) &amp;&amp; (1 &lt;= ((((int)threadIdx.x) + 8) % 9))) &amp;&amp; (((((int)threadIdx.x) + 8) % 9) &lt; 8)) ? data[((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 98) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+    if (((int)threadIdx.x) &lt; 56) {
+      pad_temp_shared[(((int)threadIdx.x) + 196)] = ((((2 &lt;= ((int)threadIdx.x)) &amp;&amp; (1 &lt;= ((((int)threadIdx.x) + 7) % 9))) &amp;&amp; (((((int)threadIdx.x) + 7) % 9) &lt; 8)) ? data[((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 196) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
     }
+    kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) % 12) / 3) * 9)) + (((int)threadIdx.x) % 3))];
+    if (((int)threadIdx.x) &lt; 94) {
+      kernel_shared[(((int)threadIdx.x) + 98)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 98) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 2) % 12) / 3) * 9)) + ((((int)threadIdx.x) + 2) % 3))];
+    }
+    __syncthreads();
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[((((int)threadIdx.x) / 49) * 96)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 12)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 1)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 13)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 2)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 14)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 24)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 36)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 25)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 37)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 26)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 38)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 48)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 60)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 49)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 61)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 50)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 62)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 72)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 84)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 73)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 85)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 74)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 86)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 3)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 15)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 4)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 16)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 5)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 17)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 27)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 39)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 28)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 40)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 29)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 41)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 51)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 63)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 52)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 64)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 53)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 65)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 75)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 87)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 76)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 88)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 77)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 89)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 6)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 18)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 7)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 19)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 8)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 20)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 30)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 42)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 31)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 43)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 32)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 44)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 54)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 66)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 55)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 67)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 56)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 68)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 78)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 90)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 79)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 91)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 80)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 92)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 9)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 21)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 10)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 22)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 11)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 23)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 33)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 45)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 34)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 46)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 35)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 47)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 57)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 69)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 58)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 70)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 59)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 71)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 81)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 93)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 82)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 94)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 83)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 95)]));
+    __syncthreads();
+    pad_temp_shared[((int)threadIdx.x)] = (((1 &lt;= (((int)threadIdx.x) % 9)) &amp;&amp; ((((int)threadIdx.x) % 9) &lt; 8)) ? data[((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 1)] : 0.000000e+00f);
+    pad_temp_shared[(((int)threadIdx.x) + 98)] = (((1 &lt;= ((((int)threadIdx.x) + 8) % 9)) &amp;&amp; (((((int)threadIdx.x) + 8) % 9) &lt; 8)) ? data[((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 98) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 1)] : 0.000000e+00f);
+    if (((int)threadIdx.x) &lt; 56) {
+      pad_temp_shared[(((int)threadIdx.x) + 196)] = (((1 &lt;= ((((int)threadIdx.x) + 7) % 9)) &amp;&amp; (((((int)threadIdx.x) + 7) % 9) &lt; 8)) ? data[((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 196) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 1)] : 0.000000e+00f);
+    }
+    kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) % 12) / 3) * 9)) + (((int)threadIdx.x) % 3)) + 3)];
+    if (((int)threadIdx.x) &lt; 94) {
+      kernel_shared[(((int)threadIdx.x) + 98)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 98) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 2) % 12) / 3) * 9)) + ((((int)threadIdx.x) + 2) % 3)) + 3)];
+    }
+    __syncthreads();
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[((((int)threadIdx.x) / 49) * 96)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 12)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 1)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 13)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 2)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 14)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 24)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 36)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 25)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 37)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 26)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 38)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 48)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 60)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 49)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 61)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 50)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 62)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 72)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 84)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 73)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 85)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 74)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 86)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 3)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 15)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 4)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 16)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 5)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 17)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 27)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 39)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 28)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 40)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 29)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 41)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 51)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 63)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 52)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 64)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 53)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 65)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 75)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 87)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 76)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 88)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 77)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 89)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 6)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 18)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 7)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 19)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 8)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 20)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 30)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 42)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 31)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 43)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 32)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 44)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 54)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 66)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 55)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 67)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 56)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 68)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 78)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 90)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 79)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 91)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 80)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 92)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 9)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 21)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 10)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 22)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 11)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 23)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 33)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 45)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 34)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 46)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 35)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 47)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 57)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 69)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 58)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 70)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 59)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 71)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 81)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 93)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 82)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 94)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 83)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 95)]));
+    __syncthreads();
+    pad_temp_shared[((int)threadIdx.x)] = (((((((int)threadIdx.x) % 63) &lt; 54) &amp;&amp; (1 &lt;= (((int)threadIdx.x) % 9))) &amp;&amp; ((((int)threadIdx.x) % 9) &lt; 8)) ? data[((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) + 6)] : 0.000000e+00f);
+    pad_temp_shared[(((int)threadIdx.x) + 98)] = ((((((((int)threadIdx.x) + 35) % 63) &lt; 54) &amp;&amp; (1 &lt;= ((((int)threadIdx.x) + 8) % 9))) &amp;&amp; (((((int)threadIdx.x) + 8) % 9) &lt; 8)) ? data[((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 98) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) + 6)] : 0.000000e+00f);
+    if (((int)threadIdx.x) &lt; 56) {
+      pad_temp_shared[(((int)threadIdx.x) + 196)] = ((((((int)threadIdx.x) &lt; 47) &amp;&amp; (1 &lt;= ((((int)threadIdx.x) + 7) % 9))) &amp;&amp; (((((int)threadIdx.x) + 7) % 9) &lt; 8)) ? data[((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 196) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) + 6)] : 0.000000e+00f);
+    }
+    kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) % 12) / 3) * 9)) + (((int)threadIdx.x) % 3)) + 6)];
+    if (((int)threadIdx.x) &lt; 94) {
+      kernel_shared[(((int)threadIdx.x) + 98)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 98) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 2) % 12) / 3) * 9)) + ((((int)threadIdx.x) + 2) % 3)) + 6)];
+    }
+    __syncthreads();
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[((((int)threadIdx.x) / 49) * 96)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 12)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 1)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 13)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 2)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 14)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 24)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 36)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 25)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 37)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 26)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 38)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 48)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 60)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 49)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 61)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 50)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 62)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 72)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 84)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 73)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 85)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 74)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 86)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 3)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 15)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 4)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 16)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 5)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 17)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 27)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 39)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 28)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 40)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 29)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 41)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 51)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 63)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 52)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 64)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 53)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 65)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 75)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 87)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 76)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 88)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 77)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 89)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 6)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 18)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 7)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 19)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 8)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 20)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 30)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 42)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 31)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 43)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 32)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 44)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 54)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 66)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 55)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 67)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 56)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 68)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 78)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 90)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 79)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 91)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 80)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 92)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 9)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 21)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 10)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 22)]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 11)]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 23)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 33)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 45)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 34)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 46)]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 35)]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 47)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 57)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 69)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 58)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 70)]));
+    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 59)]));
+    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 71)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 81)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 93)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 82)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 94)]));
+    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 83)]));
+    conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 96) + 95)]));
   }
   for (int i1_inner = 0; i1_inner &lt; 8; ++i1_inner) {
-    compute[(((((int)blockIdx.x) * 392) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 8) + i1_inner)]), 0.000000e+00f);
+    compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 49) * 392)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 49) * 8)) + i1_inner)]), 0.000000e+00f);
   }
 }
 </pre></div>
@@ -770,7 +1367,7 @@ In the example below we resume the status and do more 5 trials.</p>
 Get devices for measurement successfully!
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes  35.577 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes  36.234 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 3f511eadd9..649d999dfe 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -916,7 +916,7 @@ so we can read the log file and load the best schedules.</p>
 Evaluate inference time cost...
 Execution time summary:
  mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)
-   7.8537       7.8488       7.8643       7.8479       0.0075
+   7.8445       7.8400       7.8543       7.8393       0.0069
 </pre></div>
 </div>
 </div>
@@ -938,7 +938,7 @@ to learn how to use the RPC Tracker and RPC Server.
 To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
 with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
 </ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  6.985 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  6.080 seconds)</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-network-cuda-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/eafe360d52540634c9eea0fa89e804bd/tune_network_cuda.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tune_network_cuda.py</span></code></a></p>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
index 114220d1f4..107dfe5ee8 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -935,7 +935,7 @@ so we can read the log file and load the best schedules.</p>
 Evaluate inference time cost...
 Execution time summary:
  mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)
-  763.4786     763.5029     764.6758     762.2570      0.9876
+  753.6344     752.6742     755.7805     752.4486      1.5203
 </pre></div>
 </div>
 </div>
@@ -957,7 +957,7 @@ to learn how to use the RPC Tracker and RPC Server.
 To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
 with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
 </ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  40.746 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  39.092 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 4a61873e6a..698b7ce051 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -635,13 +635,13 @@ class Module:
         placeholder_8 = T.match_buffer(placeholder_3, (33,), &quot;int32&quot;)
         placeholder_9 = T.match_buffer(placeholder_4, (128, 512))
         compute_1 = T.match_buffer(compute, (128, 512))
-        for i0_outer_i1_outer_fused in T.parallel(256):
-            compute_2 = T.allocate([256], &quot;float32&quot;, &quot;global&quot;)
-            compute_3 = T.buffer_decl((256,), data=compute_2)
+        for i0_outer_i1_outer_fused in T.parallel(128):
+            compute_2 = T.allocate([512], &quot;float32&quot;, &quot;global&quot;)
+            compute_3 = T.buffer_decl((512,), data=compute_2)
             for nb_j_inner in range(2):
-                for i_inner_init, j_init in T.grid(8, 16):
+                for i_inner_init, j_init in T.grid(16, 16):
                     compute_3[i_inner_init * 32 + nb_j_inner * 16 + j_init] = T.float32(0)
-                for elem_idx, i_inner, j in T.grid(T.let(cse_var_1, i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner, placeholder_10[cse_var_1 + 1] - placeholder_10[cse_var_1]), 8, 16):
+                for elem_idx, i_inner, j in T.grid(T.let(cse_var_1, i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner, placeholder_10[cse_var_1 + 1] - placeholder_10[cse_var_1]), 16, 16):
                     cse_var_1 = T.var(&quot;int32&quot;)
                     placeholder_10 = T.buffer_decl((33,), &quot;int32&quot;, data=placeholder_8.data)
                     cse_var_3: T.int32 = i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner
@@ -649,12 +649,12 @@ class Module:
                     placeholder_11 = T.buffer_decl((78656,), data=placeholder_6.data)
                     placeholder_12 = T.buffer_decl((32768,), data=placeholder_5.data)
                     placeholder_13 = T.buffer_decl((4916,), &quot;int32&quot;, data=placeholder_7.data)
-                    compute_3[cse_var_2] = compute_3[cse_var_2] + placeholder_11[placeholder_10[cse_var_3] * 16 + elem_idx * 16 + j] * T.max(placeholder_12[i0_outer_i1_outer_fused // 16 * 2048 + i_inner * 256 + placeholder_13[placeholder_10[cse_var_3] + elem_idx]], T.float32(0))
-            for i0_inner in range(8):
-                cse_var_4: T.int32 = i0_outer_i1_outer_fused // 16 * 4096 + i0_inner * 512 + i0_outer_i1_outer_fused % 16 * 32
+                    compute_3[cse_var_2] = compute_3[cse_var_2] + placeholder_11[placeholder_10[cse_var_3] * 16 + elem_idx * 16 + j] * T.max(placeholder_12[i0_outer_i1_outer_fused // 16 * 4096 + i_inner * 256 + placeholder_13[placeholder_10[cse_var_3] + elem_idx]], T.float32(0))
+            for i0_inner, i1_inner in T.grid(16, 32):
+                cse_var_4: T.int32 = i0_outer_i1_outer_fused // 16 * 8192 + i0_inner * 512 + i0_outer_i1_outer_fused % 16 * 32 + i1_inner
                 compute_4 = T.buffer_decl((65536,), data=compute_1.data)
                 placeholder_10 = T.buffer_decl((65536,), data=placeholder_9.data)
-                compute_4[cse_var_4:cse_var_4 + 32] = T.max(compute_3[i0_inner * 32:i0_inner * 32 + 32] + placeholder_10[cse_var_4:cse_var_4 + 32], T.Broadcast(T.float32(0), 32))
+                compute_4[cse_var_4] = T.max(compute_3[i0_inner * 32 + i1_inner] + placeholder_10[cse_var_4], T.float32(0))
 </pre></div>
 </div>
 </div>
@@ -688,7 +688,7 @@ class Module:
 <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: 1.658 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.528 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 b4937e7d03..c74cb0e04c 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -340,7 +340,7 @@
             
   <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>00:47.104</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:32.631</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 84%" />
@@ -349,11 +349,11 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:47.070</p></td>
+<td><p>00:32.597</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
-<td><p>00:00.020</p></td>
+<td><p>00:00.021</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></td>
@@ -361,7 +361,7 @@
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></td>
-<td><p>00:00.005</p></td>
+<td><p>00:00.004</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_mobile_gpu.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-mobile-gpu-py"><span class="std std-ref">Auto-tuning a Convolutional Network for Mobile GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_mobile_gpu.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 9d8fe36be6..44265bbf2a 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -568,27 +568,7 @@ for this template</p>
 waiting for device...
 device available
 Get devices for measurement successfully!
-No: 1   GFLOPS: 4.06/4.06       result: MeasureResult(costs=(0.0569717215,), error_no=MeasureErrorNo.NO_ERROR, all_cost=7.68753981590271, timestamp=1674075708.6732135) [(&#39;tile_f&#39;, [-1, 2, 2, 16]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 8, 1]), (&#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,10272631
-No: 2   GFLOPS: 0.00/4.06       result: Traceback (most recent call last):
-  File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 142, in build
-    res = future.result()
-  File &quot;/usr/lib/python3.7/concurrent/futures/_base.py&quot;, line 435, in result
-    return self.__get_result()
-  File &quot;/usr/lib/python3.7/concurrent/futures/_base.py&quot;, line 384, in __get_result
-    raise self._exception
-  File &quot;/usr/lib/python3.7/concurrent/futures/thread.py&quot;, line 57, in run
-    result = self.fn(*self.args, **self.kwargs)
-  File &quot;/workspace/python/tvm/contrib/popen_pool.py&quot;, line 432, in &lt;lambda&gt;
-    worker = lambda *args: self._worker_run(*args)
-  File &quot;/workspace/python/tvm/contrib/popen_pool.py&quot;, line 401, in _worker_run
-    return proc.recv()
-  File &quot;/workspace/python/tvm/contrib/popen_pool.py&quot;, line 309, in recv
-    raise TimeoutError()
-TimeoutError
-
-        [(&#39;tile_f&#39;, [-1, 32, 2, 4]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 7]), (&#39;tile_rc&#39;, [-1, 2, 4]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 1)],None,9172793
-No: 3   GFLOPS: 70.10/70.10     result: MeasureResult(costs=(0.0033024939032258067,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.2502856254577637, timestamp=1674075710.3525412)      [(&#39;tile_f&#39;, [-1, 4, 16, 2]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 8, 1]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 0)],None,4465867
-No: 4   GFLOPS: 0.00/70.10      result: Traceback (most recent call last):
+No: 1   GFLOPS: 0.00/0.00       result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 592, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 544, in _build_func_common
@@ -710,8 +690,8 @@ Traceback (most recent call last):
   File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 56, in tvm._ffi._cy3.core.tvm_callback
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 875, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 4, 1, 64]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 16, 8]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 1)],None,9208522
-No: 5   GFLOPS: 0.00/70.10      result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 8, 8, 4]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 8, 64]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 1)],None,8688804
+No: 2   GFLOPS: 0.00/0.00       result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 592, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 544, in _build_func_common
@@ -833,8 +813,10 @@ Traceback (most recent call last):
   File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 56, in tvm._ffi._cy3.core.tvm_callback
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 875, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 64, 2, 4]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#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,5091574
-No: 6   GFLOPS: 0.00/70.10      result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 256, 1, 2]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 64, 8]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 1)],None,8247863
+No: 3   GFLOPS: 6.58/6.58       result: MeasureResult(costs=(0.035200592,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7256617546081543, timestamp=1674083387.1573093)        [(&#39;tile_f&#39;, [-1, 16, 2, 4]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 1, 4]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 0)],None,2778052
+No: 4   GFLOPS: 424.77/424.77   result: MeasureResult(costs=(0.0005450040850340136,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8987197875976562, timestamp=1674083388.1656663)      [(&#39;tile_f&#39;, [-1, 1, 4, 1]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 8, 2]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 1)],None,6048699
+No: 5   GFLOPS: 0.00/424.77     result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 592, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 544, in _build_func_common
@@ -956,8 +938,9 @@ Traceback (most recent call last):
   File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 56, in tvm._ffi._cy3.core.tvm_callback
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 875, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 16, 2, 4]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 7]), (&#39;tile_rc&#39;, [-1, 16, 8]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 0)],None,4177692
-No: 7   GFLOPS: 0.00/70.10      result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 4, 2, 1]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 16, 8]), (&#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,10176552
+No: 6   GFLOPS: 6.20/424.77     result: MeasureResult(costs=(0.0373385695,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.085918426513672, timestamp=1674083391.4190078)        [(&#39;tile_f&#39;, [-1, 2, 2, 1]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 8, 8]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 0)],None,1655511
+No: 7   GFLOPS: 0.00/424.77     result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 592, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 544, in _build_func_common
@@ -1079,8 +1062,9 @@ Traceback (most recent call last):
   File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 56, in tvm._ffi._cy3.core.tvm_callback
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 875, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 1, 64, 2]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 7]), (&#39;tile_rc&#39;, [-1, 2, 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,6955174
-No: 8   GFLOPS: 0.00/70.10      result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 16, 16, 2]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 1, 8]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 0)],None,482329
+No: 8   GFLOPS: 326.31/424.77   result: MeasureResult(costs=(0.0007094430223214285,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.420546054840088, timestamp=1674083393.400589)        [(&#39;tile_f&#39;, [-1, 1, 2, 2]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 1, 32]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 0)],None,723864
+No: 9   GFLOPS: 0.00/424.77     result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 592, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 544, in _build_func_common
@@ -1202,8 +1186,10 @@ Traceback (most recent call last):
   File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 56, in tvm._ffi._cy3.core.tvm_callback
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 875, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 1, 16, 8]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 7]), (&#39;tile_rc&#39;, [-1, 256, 2]), (&#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;, 1)],None,9552558
-No: 9   GFLOPS: 0.00/70.10      result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 8, 4, 2]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 64, 8]), (&#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,2246055
+No: 10  GFLOPS: 3.03/424.77     result: MeasureResult(costs=(0.076422142,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0677151679992676, timestamp=1674083400.2040286)        [(&#39;tile_f&#39;, [-1, 4, 2, 32]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 2, 4]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 0)],None,264852
+No: 11  GFLOPS: 5.79/424.77     result: MeasureResult(costs=(0.0399865835,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.994432687759399, timestamp=1674083401.1428769)        [(&#39;tile_f&#39;, [-1, 2, 1, 8]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 8, 8]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 0)],None,5139557
+No: 12  GFLOPS: 0.00/424.77     result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 592, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 544, in _build_func_common
@@ -1325,8 +1311,8 @@ Traceback (most recent call last):
   File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 56, in tvm._ffi._cy3.core.tvm_callback
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 875, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 1, 8, 64]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 128, 1]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 1)],None,9706829
-No: 10  GFLOPS: 0.00/70.10      result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 1, 128, 2]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 16, 4]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 1)],None,5695457
+No: 13  GFLOPS: 0.00/424.77     result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 592, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 544, in _build_func_common
@@ -1448,8 +1434,8 @@ Traceback (most recent call last):
   File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 56, in tvm._ffi._cy3.core.tvm_callback
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 875, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 4, 8, 4]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 7]), (&#39;tile_rc&#39;, [-1, 16, 16]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 1)],None,9816963
-No: 11  GFLOPS: 0.00/70.10      result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 4, 2, 1]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 512, 1]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 1)],None,8164872
+No: 14  GFLOPS: 0.00/424.77     result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 592, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 544, in _build_func_common
@@ -1571,8 +1557,8 @@ Traceback (most recent call last):
   File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 56, in tvm._ffi._cy3.core.tvm_callback
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 875, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 2, 2, 32]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 1, 256]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 0)],None,1345931
-No: 12  GFLOPS: 0.00/70.10      result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 4, 2, 2]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 2, 64]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 0)],None,1712986
+No: 15  GFLOPS: 0.00/424.77     result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 592, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 544, in _build_func_common
@@ -1694,8 +1680,8 @@ Traceback (most recent call last):
   File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 56, in tvm._ffi._cy3.core.tvm_callback
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 875, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 8, 16, 1]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 4, 4]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 0)],None,4333157
-No: 13  GFLOPS: 0.00/70.10      result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 16, 1, 16]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 7]), (&#39;tile_rc&#39;, [-1, 4, 32]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 0)],None,4603888
+No: 16  GFLOPS: 0.00/424.77     result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 592, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 544, in _build_func_common
@@ -1817,8 +1803,8 @@ Traceback (most recent call last):
   File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 56, in tvm._ffi._cy3.core.tvm_callback
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 875, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 4, 4, 8]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 64, 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;, 1)],None,10156231
-No: 14  GFLOPS: 0.00/70.10      result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 128, 2, 2]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 32, 16]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 0)],None,911971
+No: 17  GFLOPS: 0.00/424.77     result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 592, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 544, in _build_func_common
@@ -1940,8 +1926,8 @@ Traceback (most recent call last):
   File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 56, in tvm._ffi._cy3.core.tvm_callback
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 875, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 8, 8, 2]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 2, 16]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 1)],None,9417402
-No: 15  GFLOPS: 0.00/70.10      result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 8, 8, 8]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#39;tile_x&#39;, [-1, 1, 1, 7]), (&#39;tile_rc&#39;, [-1, 16, 1]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 1)],None,5438337
+No: 18  GFLOPS: 0.00/424.77     result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 592, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 544, in _build_func_common
@@ -2063,9 +2049,8 @@ Traceback (most recent call last):
   File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 56, in tvm._ffi._cy3.core.tvm_callback
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 875, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 2, 1, 128]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 128, 1]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 0)],None,1381151
-No: 16  GFLOPS: 309.06/309.06   result: MeasureResult(costs=(0.0007490498333333333,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.328589677810669, timestamp=1674075715.4546165)       [(&#39;tile_f&#39;, [-1, 2, 4, 2]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 8, 2]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 0)],None,1790213
-No: 17  GFLOPS: 0.00/309.06     result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 1, 2, 64]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 1, 512]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 0)],None,3870224
+No: 19  GFLOPS: 0.00/424.77     result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 592, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 544, in _build_func_common
@@ -2187,161 +2172,8 @@ Traceback (most recent call last):
   File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 56, in tvm._ffi._cy3.core.tvm_callback
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 875, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 4, 2, 4]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 7]), (&#39;tile_rc&#39;, [-1, 64, 4]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 0)],None,3962750
-No: 18  GFLOPS: 0.00/309.06     result: Traceback (most recent call last):
-  File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 742, in __call__
-    yield remote, remote.load_module(os.path.split(build_result.filename)[1])
-  File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 706, in run_through_rpc
-    costs = time_f(*args).results
-  File &quot;/workspace/python/tvm/runtime/module.py&quot;, line 357, in evaluator
-    blob = feval(*args)
-  File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
-  File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 262, in tvm._ffi._cy3.core.FuncCall
-  File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 251, in tvm._ffi._cy3.core.FuncCall3
-  File &quot;tvm/_ffi/_cython/./base.pxi&quot;, line 181, in tvm._ffi._cy3.core.CHECK_CALL
-tvm._ffi.base.TVMError: Traceback (most recent call last):
-  4: TVMFuncCall
-        at ../src/runtime/c_runtime_api.cc:477
-  3: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
-        at ../include/tvm/runtime/packed_func.h:1217
-  2: tvm::runtime::RPCWrappedFunc::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
-        at ../src/runtime/rpc/rpc_module.cc:129
-  1: tvm::runtime::RPCClientSession::CallFunc(void*, TVMValue const*, int const*, int, std::function&lt;void (tvm::runtime::TVMArgs)&gt; const&amp;)
-        at ../src/runtime/rpc/rpc_endpoint.cc:1012
-  0: tvm::runtime::RPCEndpoint::CallFunc(void*, TVMValue const*, int const*, int, std::function&lt;void (tvm::runtime::TVMArgs)&gt;)
-        at ../src/runtime/rpc/rpc_endpoint.cc:804
-  File &quot;../src/runtime/rpc/rpc_endpoint.cc&quot;, line 804
-TVMError:
----------------------------------------------------------------
-An error occurred during the execution of TVM.
-For more information, please see: https://tvm.apache.org/docs/errors.html
----------------------------------------------------------------
-  Check failed: (code == RPCCode::kReturn) is false: code=kShutdown
-
-During handling of the above exception, another exception occurred:
-
-Traceback (most recent call last):
-  File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 706, in run_through_rpc
-    costs = time_f(*args).results
-  File &quot;/usr/lib/python3.7/contextlib.py&quot;, line 130, in __exit__
-    self.gen.throw(type, value, traceback)
-  File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 746, in __call__
-    remote.remove(build_result.filename)
-  File &quot;/workspace/python/tvm/rpc/client.py&quot;, line 144, in remove
-    self._remote_funcs[&quot;remove&quot;] = self.get_function(&quot;tvm.rpc.server.remove&quot;)
-  File &quot;/workspace/python/tvm/rpc/client.py&quot;, line 72, in get_function
-    return self._sess.get_function(name)
-  File &quot;/workspace/python/tvm/runtime/module.py&quot;, line 171, in get_function
-    self.handle, c_str(name), ctypes.c_int(query_imports), ctypes.byref(ret_handle)
-  File &quot;/workspace/python/tvm/_ffi/base.py&quot;, line 348, in check_call
-    raise get_last_ffi_error()
-tvm._ffi.base.TVMError: Traceback (most recent call last):
-  52: 0xffffffffffffffff
-  51: _start
-  50: __libc_start_main
-  49: _Py_UnixMain
-  48: 0x0000000000650da0
-  47: 0x0000000000650afa
-  46: _PyFunction_FastCallDict
-  45: _PyEval_EvalCodeWithName
-  44: _PyEval_EvalFrameDefault
-  43: _PyFunction_FastCallKeywords
-  42: _PyEval_EvalCodeWithName
-  41: _PyEval_EvalFrameDefault
-  40: _PyMethodDef_RawFastCallKeywords
-  39: 0x0000000000546369
-  38: _PyEval_EvalCodeWithName
-  37: _PyEval_EvalFrameDefault
-  36: _PyFunction_FastCallKeywords
-  35: _PyEval_EvalCodeWithName
-  34: _PyEval_EvalFrameDefault
-  33: _PyFunction_FastCallDict
-  32: _PyEval_EvalCodeWithName
-  31: _PyEval_EvalFrameDefault
-  30: _PyObject_FastCallDict
-  29: 0x00000000004c06e1
-  28: _PyFunction_FastCallDict
-  27: _PyEval_EvalFrameDefault
-  26: _PyMethodDescr_FastCallKeywords
-  25: 0x00000000005dcb58
-  24: 0x00000000005dc83f
-  23: 0x00000000004ba127
-  22: _PyEval_EvalFrameDefault
-  21: _PyFunction_FastCallKeywords
-  20: _PyEval_EvalFrameDefault
-  19: _PyFunction_FastCallKeywords
-  18: _PyEval_EvalFrameDefault
-  17: _PyFunction_FastCallKeywords
-  16: _PyEval_EvalCodeWithName
-  15: _PyEval_EvalFrameDefault
-  14: 0x0000000000537c30
-  13: _PyObject_FastCallKeywords
-  12: 0x00007f95138f1fa2
-  11: _ctypes_callproc
-  10: ffi_call
-  9: ffi_call_unix64
-  8: TVMModGetFunction
-        at ../src/runtime/c_runtime_api.cc:408
-  7: tvm::runtime::ModuleNode::GetFunction(std::__cxx11::basic_string&lt;char, std::char_traits&lt;char&gt;, std::allocator&lt;char&gt; &gt; const&amp;, bool)
-        at ../src/runtime/module.cc:66
-  6: tvm::runtime::RPCModuleNode::GetFunction(std::__cxx11::basic_string&lt;char, std::char_traits&lt;char&gt;, std::allocator&lt;char&gt; &gt; const&amp;, tvm::runtime::ObjectPtr&lt;tvm::runtime::Object&gt; const&amp;)
-        at ../src/runtime/rpc/rpc_module.cc:185
-  5: tvm::runtime::RPCClientSession::GetFunction(std::__cxx11::basic_string&lt;char, std::char_traits&lt;char&gt;, std::allocator&lt;char&gt; &gt; const&amp;)
-        at ../src/runtime/rpc/rpc_endpoint.cc:1007
-  4: tvm::runtime::TVMRetValue tvm::runtime::RPCEndpoint::SysCallRemote&lt;std::__cxx11::basic_string&lt;char, std::char_traits&lt;char&gt;, std::allocator&lt;char&gt; &gt; const&amp;&gt;(tvm::runtime::RPCCode, std::__cxx11::basic_string&lt;char, std::char_traits&lt;char&gt;, std::allocator&lt;char&gt; &gt; const&amp;)
-        at ../src/runtime/rpc/rpc_endpoint.h:223
-  3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()&lt;int, std::__cxx11::basic_string&lt;char, std::char_traits&lt;char&gt;, std::allocator&lt;char&gt; &gt; const&amp;&gt;(int&amp;&amp;, std::__cxx11::basic_string&lt;char, std::char_traits&lt;char&gt;, std::allocator&lt;char&gt; &gt; const&amp;) const
-        at ../include/tvm/runtime/packed_func.h:1617
-  2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
-        at ../include/tvm/runtime/packed_func.h:1217
-  1: Call
-        at ../include/tvm/runtime/packed_func.h:1213
-  0: operator()
-        at ../src/runtime/rpc/rpc_endpoint.cc:684
-  File &quot;../src/runtime/rpc/rpc_endpoint.cc&quot;, line 684
-TVMError:
----------------------------------------------------------------
-An error occurred during the execution of TVM.
-For more information, please see: https://tvm.apache.org/docs/errors.html
----------------------------------------------------------------
-  Check failed: (code == RPCCode::kReturn) is false: code=1
-
-Traceback (most recent call last):
-  52: 0xffffffffffffffff
-  51: _start
-  50: __libc_start_main
-  49: _Py_UnixMain
-  48: 0x0000000000650da0
-  47: 0x0000000000650afa
-  46: _PyFunction_FastCallDict
-  45: _PyEval_EvalCodeWithName
-  44: _PyEval_EvalFrameDefault
-  43: _PyFunction_FastCallKeywords
-  42: _PyEval_EvalCodeWithName
-  41: _PyEval_EvalFrameDefault
-  40: _PyMethodDef_RawFastCallKeywords
-  39: 0x0000000000546369
-  38: _PyEval_EvalCodeWithName
-  37: _PyEval_EvalFrameDefault
-  36: _PyFunction_FastCallKeywords
-  35: _PyEval_EvalCodeWithName
-  34: _PyEval_EvalFrameDefault
-  33: _PyFunction_FastCallDict
-  32: _PyEval_EvalCodeWithName
-  31: _PyEval_EvalFrameDefault
-  30: _PyObject_FastCallDict
-  29: 0x00000000004c06e1
-  28: _PyFunction_FastCallDict
-  27: _PyEval_EvalFrameDefault
-  26: _PyMethodDescr_FastCallKeywords
-  25: 0x00000000005dcb58
-  24: 0x00000000005dc83f
-  23: 0x00000000004ba127
-  22: _PyEval_EvalFrameDefault
-  21: _PyFunction_FastCallKeywords
-  20: _PyEval_EvalFrameDefault
-  19: _PyFunction_FastCall      [(&#39;tile_f&#39;, [-1, 1, 1, 1]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 8, 64]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 0)],None,750640
-No: 19  GFLOPS: 0.00/309.06     result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 4, 32, 2]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 128, 2]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 0)],None,3353552
+No: 20  GFLOPS: 0.00/424.77     result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 592, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 544, in _build_func_common
@@ -2463,8 +2295,7 @@ Traceback (most recent call last):
   File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 56, in tvm._ffi._cy3.core.tvm_callback
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 875, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 2, 1, 32]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 64, 1]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 0)],None,3314046
-No: 20  GFLOPS: 30.02/309.06    result: MeasureResult(costs=(0.007710311230769231,), error_no=MeasureErrorNo.NO_ERROR, all_cost=10.001625537872314, timestamp=1674075730.2298257)       [(&#39;tile_f&#39;, [-1, 1, 1, 32]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 16, 4]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 0)],None,3568365
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 4, 1, 1]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 1, 512]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 0)],None,2127402
 </pre></div>
 </div>
 <p>Finally we can inspect the best config from log file, check correctness,
@@ -2503,9 +2334,9 @@ and measure running time.</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Finish loading 20 records
 
 Best config:
-[(&#39;tile_f&#39;, [-1, 2, 4, 2]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 8, 2]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 0)],None,1790213
+[(&#39;tile_f&#39;, [-1, 1, 4, 1]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 8, 2]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 1)],None,6048699
 Finish loading 20 records
-Time cost of this operator: 0.001066
+Time cost of this operator: 0.000883
 </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 95c9563a24..0eb694fc47 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -646,10 +646,10 @@ the tuned operator.</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build without Autotuning ##########
 Node Name                                     Ops                                           Time(us)  Time(%)  Shape              Inputs  Outputs  Measurements(us)
 ---------                                     ---                                           --------  -------  -----              ------  -------  ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  311.5     98.719   (1, 2, 10, 10, 3)  2       1        [311.5]
-tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       3.071     0.973    (1, 6, 10, 10)     1       1        [3.071]
-tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.97      0.308    (1, 1, 10, 10, 3)  1       1        [0.97]
-Total_time                                    -                                             315.541   -        -                  -       -        -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  312.4     98.732   (1, 2, 10, 10, 3)  2       1        [312.4]
+tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       3.024     0.956    (1, 6, 10, 10)     1       1        [3.024]
+tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.988     0.312    (1, 1, 10, 10, 3)  1       1        [0.988]
+Total_time                                    -                                             316.412   -        -                  -       -        -
 </pre></div>
 </div>
 </div>
@@ -701,10 +701,10 @@ Total_time                                    -
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build with Autotuning ##########
 Node Name                                     Ops                                           Time(us)  Time(%)  Shape              Inputs  Outputs  Measurements(us)
 ---------                                     ---                                           --------  -------  -----              ------  -------  ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  134.4     97.944   (1, 6, 10, 10, 1)  2       1        [134.4]
-tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       1.833     1.336    (1, 6, 10, 10)     1       1        [1.833]
-tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.987     0.72     (1, 1, 10, 10, 3)  1       1        [0.987]
-Total_time                                    -                                             137.221   -        -                  -       -        -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  109.3     97.657   (1, 6, 10, 10, 1)  2       1        [109.3]
+tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       1.775     1.586    (1, 6, 10, 10)     1       1        [1.775]
+tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.847     0.757    (1, 3, 10, 10, 1)  1       1        [0.847]
+Total_time                                    -                                             111.923   -        -                  -       -        -
 </pre></div>
 </div>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/micro_pytorch.html b/docs/how_to/work_with_microtvm/micro_pytorch.html
index d300980106..0719492e91 100644
--- a/docs/how_to/work_with_microtvm/micro_pytorch.html
+++ b/docs/how_to/work_with_microtvm/micro_pytorch.html
@@ -453,7 +453,8 @@ download a cat image and preprocess it to use as the model input.</p>
 Downloading: &quot;https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth&quot; to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
 
   0%|          | 0.00/3.42M [00:00&lt;?, ?B/s]
-100%|##########| 3.42M/3.42M [00:00&lt;00:00, 45.9MB/s]
+ 61%|######    | 2.09M/3.42M [00:00&lt;00:00, 21.1MB/s]
+100%|##########| 3.42M/3.42M [00:00&lt;00:00, 32.5MB/s]
 /workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
   return LooseVersion(torch_ver) &gt; ver
 /venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -577,7 +578,7 @@ via the host <cite>main.cc`</cite> or if a Zephyr emulated board is selected as
 Torch top-1 id: 282, class name: tiger cat
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  11.832 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  10.557 seconds)</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-pytorch-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/12b9ecc04c41abaa12022061771821d1/micro_pytorch.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">micro_pytorch.py</span></code></a></p>
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index df9fa17023..844a7a26cc 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -523,7 +523,7 @@ 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/tmpkzt99nrx/images/random&#39;
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>&#39;/tmp/tmp7s9ljeud/images/random&#39;
 </pre></div>
 </div>
 </div>
@@ -583,8 +583,8 @@ 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="[0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpkzt99nrx/images/target contains 8144 images
-/tmp/tmpkzt99nrx/images/random contains 5000 images
+<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmp7s9ljeud/images/target contains 8144 images
+/tmp/tmp7s9ljeud/images/random contains 5000 images
 </pre></div>
 </div>
 </div>
@@ -696,13 +696,13 @@ the time on our validation set).</p>
 </pre></div>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 47s - loss: 0.2224 - accuracy: 0.9233 - val_loss: 0.1460 - val_accuracy: 0.9471 - 47s/epoch - 144ms/step
+328/328 - 47s - loss: 0.2046 - accuracy: 0.9263 - val_loss: 0.1429 - val_accuracy: 0.9569 - 47s/epoch - 144ms/step
 Epoch 2/3
-328/328 - 44s - loss: 0.0965 - accuracy: 0.9635 - val_loss: 0.1448 - val_accuracy: 0.9532 - 44s/epoch - 133ms/step
+328/328 - 44s - loss: 0.0962 - accuracy: 0.9633 - val_loss: 0.1475 - val_accuracy: 0.9524 - 44s/epoch - 133ms/step
 Epoch 3/3
-328/328 - 44s - loss: 0.0757 - accuracy: 0.9742 - val_loss: 0.1207 - val_accuracy: 0.9585 - 44s/epoch - 133ms/step
+328/328 - 44s - loss: 0.0661 - accuracy: 0.9755 - val_loss: 0.1311 - val_accuracy: 0.9622 - 44s/epoch - 133ms/step
 
-&lt;keras.callbacks.History object at 0x7f43f4bcb450&gt;
+&lt;keras.callbacks.History object at 0x7fb54fc009d0&gt;
 </pre></div>
 </div>
 </div>
@@ -962,7 +962,7 @@ 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  6.318 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes  12.154 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 52225b3e18..8c1b764714 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -340,7 +340,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>07:24.742</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>07:28.452</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 83%" />
@@ -349,23 +349,23 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>05:06.318</p></td>
+<td><p>05:12.154</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="micro_pytorch.html#sphx-glr-how-to-work-with-microtvm-micro-pytorch-py"><span class="std std-ref">microTVM PyTorch Tutorial</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_pytorch.py</span></code>)</p></td>
-<td><p>01:11.832</p></td>
+<td><p>01:10.557</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:53.832</p></td>
+<td><p>00:52.901</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="micro_aot.html#sphx-glr-how-to-work-with-microtvm-micro-aot-py"><span class="std std-ref">microTVM Host-Driven AoT</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:08.773</p></td>
+<td><p>00:08.926</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:03.987</p></td>
+<td><p>00:03.914</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><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 4bcf0f649c..3bbc31f96a 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -340,7 +340,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:45.287</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:45.233</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 84%" />
@@ -349,15 +349,15 @@
 </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>00:32.667</p></td>
+<td><p>00:33.298</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></td>
-<td><p>00:10.208</p></td>
+<td><p>00:10.387</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>00:02.406</p></td>
+<td><p>00:01.542</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 7cf6dbd8c0..74f8aa689b 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -535,7 +535,7 @@ 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 0x7f436d0af3b0&gt;
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>&lt;function my_cuda_math_rule at 0x7fb54faeb3b0&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 245636b2f7..bac0e1d5da 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -340,7 +340,7 @@
             
   <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>00:04.601</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:08.046</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 83%" />
@@ -349,31 +349,31 @@
 </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>00:02.230</p></td>
+<td><p>00:05.510</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="tensorize.html#sphx-glr-how-to-work-with-schedules-tensorize-py"><span class="std std-ref">Use Tensorize to Leverage Hardware Intrinsics</span></a> (<code class="docutils literal notranslate"><span class="pre">tensorize.py</span></code>)</p></td>
-<td><p>00:01.051</p></td>
+<td><p>00:01.152</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>00:00.546</p></td>
+<td><p>00:00.591</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>00:00.545</p></td>
+<td><p>00:00.568</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="extern_op.html#sphx-glr-how-to-work-with-schedules-extern-op-py"><span class="std std-ref">External Tensor Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">extern_op.py</span></code>)</p></td>
-<td><p>00:00.118</p></td>
+<td><p>00:00.117</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>00:00.053</p></td>
+<td><p>00:00.050</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>00:00.032</p></td>
+<td><p>00:00.033</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 977459a2fa..e105270b0e 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -586,7 +586,7 @@ class Module:
         B_1 = T.match_buffer(B, (512, 64))
         C_1 = T.match_buffer(C, (1024, 512))
         i = T.var(&quot;int32&quot;)
-        T.attr(T.iter_var(i, None, &quot;DataPar&quot;, &quot;&quot;), &quot;pragma_import_llvm&quot;, &quot;; ModuleID = &#39;/tmp/tmpc34m7xbo/input0.cc&#39;\nsource_filename = \&quot;/tmp/tmpc34m7xbo/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 = alloca  [...]
+        T.attr(T.iter_var(i, None, &quot;DataPar&quot;, &quot;&quot;), &quot;pragma_import_llvm&quot;, &quot;; ModuleID = &#39;/tmp/tmpovo8qjzw/input0.cc&#39;\nsource_filename = \&quot;/tmp/tmpovo8qjzw/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 = alloca  [...]
         for i, j_outer in T.grid(1024, 32):
             T.call_extern(&quot;int32&quot;, &quot;gemv_update&quot;, T.tvm_access_ptr(T.type_annotation(&quot;float32&quot;), C_1.data, i * 512 + j_outer * 16, 16, 2), T.tvm_access_ptr(T.type_annotation(&quot;float32&quot;), A_1.data, i * 64, 64, 1), T.tvm_access_ptr(T.type_annotation(&quot;float32&quot;), B_1.data, j_outer * 1024, 1024, 1), 16, 64, 64)
 </pre></div>
diff --git a/docs/install/nnpack.html b/docs/install/nnpack.html
index 23d2181e9d..1ef28de467 100644
--- a/docs/install/nnpack.html
+++ b/docs/install/nnpack.html
@@ -229,17 +229,7 @@
               <p class="caption" role="heading"><span class="caption-text">Getting Started</span></p>
 <ul class="current">
 <li class="toctree-l1 current"><a class="reference internal" href="index.html">Installing TVM</a><ul class="current">
-<li class="toctree-l2 current"><a class="reference internal" href="from_source.html">Install from Source</a><ul class="current">
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#developers-get-source-from-github">Developers: Get Source from Github</a></li>
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#build-the-shared-library">Build the Shared Library</a></li>
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#python-package-installation">Python Package Installation</a></li>
-<li class="toctree-l3 current"><a class="reference internal" href="from_source.html#install-contrib-libraries">Install Contrib Libraries</a><ul class="current">
-<li class="toctree-l4 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a></li>
-</ul>
-</li>
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#enable-c-tests">Enable C++ Tests</a></li>
-</ul>
-</li>
+<li class="toctree-l2"><a class="reference internal" href="from_source.html">Install from Source</a></li>
 <li class="toctree-l2"><a class="reference internal" href="docker.html">Docker Images</a></li>
 <li class="toctree-l2 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a><ul>
 <li class="toctree-l3"><a class="reference internal" href="#conditions">Conditions</a></li>
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index cabc893f3d..71f0e0dc4a 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1615,7 +1615,7 @@ 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>
@@ -1899,7 +1899,7 @@ 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 361c1636f5..32580132f3 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/02e8bbfab/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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 2abd55d93b..89a933d2de 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/02e8bbfab/web/src/memory.ts#L223">memory.ts:223</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/memory.ts#L208">memory.ts:208</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/memory.ts#L312">memory.ts:312</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/memory.ts#L284">memory.ts:284</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/memory.ts#L388">memory.ts:388</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/memory.ts#L376">memory.ts:376</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/memory.ts#L267">memory.ts:267</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/memory.ts#L243">memory.ts:243</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/memory.ts#L321">memory.ts:321</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/memory.ts#L252">memory.ts:252</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/memory.ts#L359">memory.ts:359</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/memory.ts#L342">memory.ts:342</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/memory.ts#L350">memory.ts:350</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/memory.ts#L326">memory.ts:326</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/memory.ts#L363">memory.ts:363</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/memory.ts#L346">memory.ts:346</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/memory.ts#L334">memory.ts:334</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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 05606bbb0d..d79c819fc5 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/02e8bbfab/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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 f97f48e86b..0e21f45a83 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/02e8bbfab/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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 5dd0e4940c..b68861de93 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/02e8bbfab/web/src/environment.ts#L86">environment.ts:86</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/environment.ts#L70">environment.ts:70</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/environment.ts#L69">environment.ts:69</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/environment.ts#L78">environment.ts:78</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/environment.ts#L84">environment.ts:84</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/environment.ts#L105">environment.ts:105</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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 abaadb3c56..2c30b2ea4f 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/02e8bbfab/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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 c82acd98ad..14b17c9540 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/02e8bbfab/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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 b2f3a934c1..80aa08b07f 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/02e8bbfab/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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 6b2952bc62..90e69d1d22 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/02e8bbfab/web/src/memory.ts#L40">memory.ts:40</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/memory.ts#L32">memory.ts:32</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/memory.ts#L33">memory.ts:33</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/memory.ts#L154">memory.ts:154</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/memory.ts#L90">memory.ts:90</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/memory.ts#L97">memory.ts:97</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/memory.ts#L74">memory.ts:74</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/memory.ts#L81">memory.ts:81</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/memory.ts#L104">memory.ts:104</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/memory.ts#L132">memory.ts:132</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/memory.ts#L145">memory.ts:145</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/memory.ts#L60">memory.ts:60</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/memory.ts#L67">memory.ts:67</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/memory.ts#L53">memory.ts:53</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/memory.ts#L114">memory.ts:114</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/memory.ts#L124">memory.ts:124</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/memory.ts#L175">memory.ts:175</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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 caca4f1966..155c38db35 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/02e8bbfab/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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 c57d1f340b..236fde9719 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/02e8bbfab/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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 267eefb2e9..f3c54cb43a 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/02e8bbfab/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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 947369c188..8eb3623c5a 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/02e8bbfab/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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 1458955f66..a58236dff5 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/02e8bbfab/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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 6345414ccf..8e0c997e56 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/02e8bbfab/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/webgpu.ts#L172">webgpu.ts:172</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/web/src/webgpu.ts#L172">webgpu.ts:172</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/02e8bbfab/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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 50d2fb4fba..f64ed35da4 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/02e8bbfab/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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 337036a4cf..a5afa9bbae 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/02e8bbfab/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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 54d020151c..2dcad4ae04 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/02e8bbfab/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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 4041f1c66e..32bf390473 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/02e8bbfab/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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 011763b409..94ca076130 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/02e8bbfab/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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 2de27447cd..faa62c54f5 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/02e8bbfab/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/support.ts#L25">support.ts:25</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/support.ts#L39">support.ts:39</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/support.ts#L52">support.ts:52</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/compact.ts#L38">compact.ts:38</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/environment.ts#L32">environment.ts:32</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/compact.ts#L24">compact.ts:24</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/support.ts#L62">support.ts:62</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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 f2495b78a3..d1941a2149 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/02e8bbfab/web/src/types.ts#L52">types.ts:52</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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 58fc5004dc..fe3d5b4006 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/02e8bbfab/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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 ce7b6df03f..b189672ec9 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/02e8bbfab/web/src/types.ts#L34">types.ts:34</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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/02e8bbfab/web/src/types.ts#L39">types.ts:39</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/5d2a94720/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 dcc6e12888..5d4e9391c6 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 1992a16539..be8ff8e145 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -340,7 +340,7 @@
             
   <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>00:31.042</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:30.513</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 82%" />
@@ -349,7 +349,7 @@
 </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>00:31.035</p></td>
+<td><p>00:30.506</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 d442276ca6..46921aad04 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -583,7 +583,7 @@ 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 33.52s!
+resnet18_v1 inference graph built in 32.51s!
 </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 4be15028da..fadde0ba3a 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -601,7 +601,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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 22.73s!
+yolov3-tiny inference graph built in 22.03s!
 </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 85547f4d41..f4f6824c42 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -340,7 +340,7 @@
             
   <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>01:39.912</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:38.379</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 84%" />
@@ -349,11 +349,11 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><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>00:50.331</p></td>
+<td><p>00:49.377</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><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>00:49.580</p></td>
+<td><p>00:49.002</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 7dd4cb424a..e588e79b84 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -340,7 +340,7 @@
             
   <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>00:03.060</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.189</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 84%" />
@@ -349,11 +349,11 @@
 </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>00:02.626</p></td>
+<td><p>00:02.717</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>00:00.434</p></td>
+<td><p>00:00.472</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 45335b6054..d196e2bb3d 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -340,7 +340,7 @@
             
   <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>00:00.783</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.837</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 81%" />
@@ -349,11 +349,11 @@
 </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>00:00.420</p></td>
+<td><p>00:00.447</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>00:00.363</p></td>
+<td><p>00:00.390</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 74fd6394f1..2427ac962a 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -570,7 +570,7 @@ class Module:
 <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: 96.807 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 93.701 ms
 </pre></div>
 </div>
 </div>
@@ -644,7 +644,7 @@ 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  14.063 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  14.570 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 4372357d99..2c9eee74db 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -680,16 +680,16 @@ 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: 12.61/12.61     result: MeasureResult(costs=(0.0212931328,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5927474498748779, timestamp=1674074176.122058)        [(&#39;tile_y&#39;, [-1, 128]), (&#39;tile_x&#39;, [-1, 512])],None,97
-No: 2   GFLOPS: 10.98/12.61     result: MeasureResult(costs=(0.0244551158,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.636193037033081, timestamp=1674074176.7659247)        [(&#39;tile_y&#39;, [-1, 256]), (&#39;tile_x&#39;, [-1, 32])],None,58
-No: 3   GFLOPS: 3.64/12.61      result: MeasureResult(costs=(0.07364926799999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4282848834991455, timestamp=1674074178.9988792)        [(&#39;tile_y&#39;, [-1, 256]), (&#39;tile_x&#39;, [-1, 16])],None,48
-No: 4   GFLOPS: 1.55/12.61      result: MeasureResult(costs=(0.17315853939999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.9932665824890137, timestamp=1674074182.8237185)        [(&#39;tile_y&#39;, [-1, 4]), (&#39;tile_x&#39;, [-1, 1])],None,2
-No: 5   GFLOPS: 4.13/12.61      result: MeasureResult(costs=(0.0650630472,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2994110584259033, timestamp=1674074184.2370825)       [(&#39;tile_y&#39;, [-1, 16]), (&#39;tile_x&#39;, [-1, 16])],None,44
-No: 6   GFLOPS: 0.83/12.61      result: MeasureResult(costs=(0.32272345839999994,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.410374402999878, timestamp=1674074189.6722739) [(&#39;tile_y&#39;, [-1, 512]), (&#39;tile_x&#39;, [-1, 2])],None,19
-No: 7   GFLOPS: 0.89/12.61      result: MeasureResult(costs=(0.299995667,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.033870697021484, timestamp=1674074195.5211098) [(&#39;tile_y&#39;, [-1, 256]), (&#39;tile_x&#39;, [-1, 2])],None,18
-No: 8   GFLOPS: 9.22/12.61      result: MeasureResult(costs=(0.029109559,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7064783573150635, timestamp=1674074196.2493129)        [(&#39;tile_y&#39;, [-1, 512]), (&#39;tile_x&#39;, [-1, 256])],None,89
-No: 9   GFLOPS: 1.76/12.61      result: MeasureResult(costs=(0.1522050992,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.6560161113739014, timestamp=1674074199.0208445)       [(&#39;tile_y&#39;, [-1, 16]), (&#39;tile_x&#39;, [-1, 2])],None,14
-No: 10  GFLOPS: 1.17/12.61      result: MeasureResult(costs=(0.22904607219999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.8800418376922607, timestamp=1674074202.94484)  [(&#39;tile_y&#39;, [-1, 1]), (&#39;tile_x&#39;, [-1, 2])],None,10
+No: 1   GFLOPS: 1.26/1.26       result: MeasureResult(costs=(0.21366675000000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.6458842754364014, timestamp=1674081857.3550878)        [(&#39;tile_y&#39;, [-1, 2]), (&#39;tile_x&#39;, [-1, 1])],None,1
+No: 2   GFLOPS: 3.29/3.29       result: MeasureResult(costs=(0.081503407,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5644311904907227, timestamp=1674081859.691211) [(&#39;tile_y&#39;, [-1, 64]), (&#39;tile_x&#39;, [-1, 8])],None,36
+No: 3   GFLOPS: 1.18/3.29       result: MeasureResult(costs=(0.226755417,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.8612968921661377, timestamp=1674081864.359341) [(&#39;tile_y&#39;, [-1, 1]), (&#39;tile_x&#39;, [-1, 2])],None,10
+No: 4   GFLOPS: 2.64/3.29       result: MeasureResult(costs=(0.1016112808,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8497552871704102, timestamp=1674081866.2368028)       [(&#39;tile_y&#39;, [-1, 512]), (&#39;tile_x&#39;, [-1, 16])],None,49
+No: 5   GFLOPS: 3.08/3.29       result: MeasureResult(costs=(0.0872327226,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.637035608291626, timestamp=1674081868.0009913)        [(&#39;tile_y&#39;, [-1, 256]), (&#39;tile_x&#39;, [-1, 8])],None,38
+No: 6   GFLOPS: 2.67/3.29       result: MeasureResult(costs=(0.10036525700000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8619179725646973, timestamp=1674081869.85988)  [(&#39;tile_y&#39;, [-1, 2]), (&#39;tile_x&#39;, [-1, 16])],None,41
+No: 7   GFLOPS: 2.10/3.29       result: MeasureResult(costs=(0.12776740339999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.294450283050537, timestamp=1674081872.9340394) [(&#39;tile_y&#39;, [-1, 128]), (&#39;tile_x&#39;, [-1, 4])],None,27
+No: 8   GFLOPS: 4.03/4.03       result: MeasureResult(costs=(0.066561712,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3215956687927246, timestamp=1674081874.2516136)        [(&#39;tile_y&#39;, [-1, 4]), (&#39;tile_x&#39;, [-1, 16])],None,42
+No: 9   GFLOPS: 13.20/13.20     result: MeasureResult(costs=(0.020334042400000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5416173934936523, timestamp=1674081874.9080758)       [(&#39;tile_y&#39;, [-1, 256]), (&#39;tile_x&#39;, [-1, 64])],None,68
+No: 10  GFLOPS: 2.40/13.20      result: MeasureResult(costs=(0.11165571999999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9915447235107422, timestamp=1674081876.9434235)        [(&#39;tile_y&#39;, [-1, 512]), (&#39;tile_x&#39;, [-1, 8])],None,39
 </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 67918a4e5b..9f2f8c5716 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -558,7 +558,7 @@ 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;: 517.6268569099921, &#39;median&#39;: 517.4762197500058, &#39;std&#39;: 2.3963316360720026}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{&#39;mean&#39;: 518.0414347700003, &#39;median&#39;: 518.4623476000013, &#39;std&#39;: 2.0786998699138803}
 </pre></div>
 </div>
 </div>
@@ -710,179 +710,178 @@ depending on the specifics of the model and the target platform.</p>
 </pre></div>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[Task  1/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  1/25]  Current/Best:   12.38/  13.43 GFLOPS | Progress: (4/20) | 8.99 s
-[Task  1/25]  Current/Best:   14.42/  19.14 GFLOPS | Progress: (8/20) | 12.29 s
-[Task  1/25]  Current/Best:   11.50/  19.14 GFLOPS | Progress: (12/20) | 15.87 s
-[Task  1/25]  Current/Best:   22.84/  23.32 GFLOPS | Progress: (16/20) | 17.99 s
-[Task  1/25]  Current/Best:   13.96/  23.32 GFLOPS | Progress: (20/20) | 20.10 s Done.
+[Task  1/25]  Current/Best:    9.55/  19.13 GFLOPS | Progress: (4/20) | 7.37 s
+[Task  1/25]  Current/Best:   10.09/  19.13 GFLOPS | Progress: (8/20) | 11.14 s
+[Task  1/25]  Current/Best:   12.92/  19.13 GFLOPS | Progress: (12/20) | 14.64 s
+[Task  1/25]  Current/Best:    7.64/  19.13 GFLOPS | Progress: (16/20) | 18.58 s
+[Task  1/25]  Current/Best:    8.52/  19.13 GFLOPS | Progress: (20/20) | 22.04 s Done.
 
 [Task  2/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  2/25]  Current/Best:    6.23/  14.51 GFLOPS | Progress: (4/20) | 3.52 s
-[Task  2/25]  Current/Best:   11.90/  14.51 GFLOPS | Progress: (8/20) | 5.41 s
-[Task  2/25]  Current/Best:   10.46/  18.78 GFLOPS | Progress: (12/20) | 8.51 s
-[Task  2/25]  Current/Best:   20.53/  20.53 GFLOPS | Progress: (16/20) | 10.23 s
-[Task  2/25]  Current/Best:    7.61/  20.53 GFLOPS | Progress: (20/20) | 11.80 s Done.
+[Task  2/25]  Current/Best:    5.41/  18.76 GFLOPS | Progress: (4/20) | 3.45 s
+[Task  2/25]  Current/Best:    6.35/  20.06 GFLOPS | Progress: (8/20) | 5.09 s
+[Task  2/25]  Current/Best:   16.43/  20.06 GFLOPS | Progress: (12/20) | 7.17 s
+[Task  2/25]  Current/Best:    5.87/  20.06 GFLOPS | Progress: (16/20) | 8.63 s
+[Task  2/25]  Current/Best:   12.58/  20.06 GFLOPS | Progress: (20/20) | 10.37 s Done.
 
 [Task  3/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  3/25]  Current/Best:   12.46/  12.46 GFLOPS | Progress: (4/20) | 5.94 s
-[Task  3/25]  Current/Best:   12.67/  18.78 GFLOPS | Progress: (8/20) | 8.45 s
-[Task  3/25]  Current/Best:   15.14/  20.46 GFLOPS | Progress: (12/20) | 10.77 s
-[Task  3/25]  Current/Best:    6.20/  20.46 GFLOPS | Progress: (16/20) | 13.01 s
-[Task  3/25]  Current/Best:   16.91/  20.46 GFLOPS | Progress: (20/20) | 15.39 s Done.
+[Task  3/25]  Current/Best:   15.68/  15.68 GFLOPS | Progress: (4/20) | 4.28 s
+[Task  3/25]  Current/Best:   13.27/  18.37 GFLOPS | Progress: (8/20) | 7.34 s
+[Task  3/25]  Current/Best:    6.76/  19.40 GFLOPS | Progress: (12/20) | 9.76 s
+[Task  3/25]  Current/Best:   16.47/  23.00 GFLOPS | Progress: (16/20) | 11.86 s
+[Task  3/25]  Current/Best:    6.64/  23.00 GFLOPS | Progress: (20/20) | 14.59 s Done.
 
 [Task  4/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  4/25]  Current/Best:   11.45/  15.76 GFLOPS | Progress: (4/20) | 7.30 s
-[Task  4/25]  Current/Best:   12.64/  17.93 GFLOPS | Progress: (8/20) | 10.10 s
-[Task  4/25]  Current/Best:    8.76/  17.93 GFLOPS | Progress: (12/20) | 15.90 s
-[Task  4/25]  Current/Best:    6.43/  17.93 GFLOPS | Progress: (16/20) | 18.57 s
-[Task  4/25]  Current/Best:   16.89/  17.93 GFLOPS | Progress: (20/20) | 21.03 s Done.
+[Task  4/25]  Current/Best:    8.46/  12.11 GFLOPS | Progress: (4/20) | 4.94 s
+[Task  4/25]  Current/Best:   16.94/  18.24 GFLOPS | Progress: (8/20) | 6.90 s
+[Task  4/25]  Current/Best:   12.93/  18.24 GFLOPS | Progress: (12/20) | 10.04 s
+[Task  4/25]  Current/Best:   11.61/  19.87 GFLOPS | Progress: (16/20) | 12.98 s
+[Task  4/25]  Current/Best:   11.00/  19.87 GFLOPS | Progress: (20/20) | 14.87 s Done.
 
 [Task  5/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  5/25]  Current/Best:   18.01/  18.01 GFLOPS | Progress: (4/20) | 3.62 s
-[Task  5/25]  Current/Best:   18.07/  18.07 GFLOPS | Progress: (8/20) | 7.33 s
-[Task  5/25]  Current/Best:    9.52/  18.07 GFLOPS | Progress: (12/20) | 10.03 s
-[Task  5/25]  Current/Best:   10.57/  18.07 GFLOPS | Progress: (16/20) | 12.66 s
-[Task  5/25]  Current/Best:   16.99/  18.07 GFLOPS | Progress: (20/20) | 15.13 s Done.
+[Task  5/25]  Current/Best:    3.05/  21.22 GFLOPS | Progress: (4/20) | 3.70 s
+[Task  5/25]  Current/Best:    9.95/  21.22 GFLOPS | Progress: (8/20) | 5.92 s
+[Task  5/25]  Current/Best:   14.24/  21.22 GFLOPS | Progress: (12/20) | 8.44 s
+[Task  5/25]  Current/Best:   17.54/  21.22 GFLOPS | Progress: (16/20) | 10.61 s
+[Task  5/25]  Current/Best:   17.70/  21.22 GFLOPS | Progress: (20/20) | 12.77 s Done.
 
 [Task  6/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  6/25]  Current/Best:   10.96/  16.01 GFLOPS | Progress: (4/20) | 5.53 s
-[Task  6/25]  Current/Best:    6.84/  16.01 GFLOPS | Progress: (8/20) | 7.99 s
-[Task  6/25]  Current/Best:   10.68/  16.01 GFLOPS | Progress: (12/20) | 12.24 s
-[Task  6/25]  Current/Best:   17.97/  22.26 GFLOPS | Progress: (16/20) | 19.11 s
-[Task  6/25]  Current/Best:   13.31/  22.26 GFLOPS | Progress: (20/20) | 21.43 s Done.
+[Task  6/25]  Current/Best:    9.43/  13.33 GFLOPS | Progress: (4/20) | 9.03 s
+[Task  6/25]  Current/Best:   17.79/  17.79 GFLOPS | Progress: (8/20) | 11.96 s
+[Task  6/25]  Current/Best:   17.60/  17.79 GFLOPS | Progress: (12/20) | 14.65 s
+[Task  6/25]  Current/Best:   17.73/  17.79 GFLOPS | Progress: (16/20) | 17.19 s
+[Task  6/25]  Current/Best:   15.20/  17.79 GFLOPS | Progress: (20/20) | 21.42 s Done.
 
 [Task  7/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  7/25]  Current/Best:   13.79/  19.27 GFLOPS | Progress: (4/20) | 3.98 s
-[Task  7/25]  Current/Best:   19.05/  19.27 GFLOPS | Progress: (8/20) | 6.42 s
-[Task  7/25]  Current/Best:    7.63/  21.17 GFLOPS | Progress: (12/20) | 8.92 s
-[Task  7/25]  Current/Best:    8.05/  21.17 GFLOPS | Progress: (16/20) | 14.09 s
-[Task  7/25]  Current/Best:   15.60/  21.17 GFLOPS | Progress: (20/20) | 16.23 s Done.
+[Task  7/25]  Current/Best:    5.95/  11.25 GFLOPS | Progress: (4/20) | 5.29 s
+[Task  7/25]  Current/Best:   11.27/  11.27 GFLOPS | Progress: (8/20) | 8.57 s
+[Task  7/25]  Current/Best:   14.01/  14.61 GFLOPS | Progress: (12/20) | 11.11 s
+[Task  7/25]  Current/Best:    5.87/  17.73 GFLOPS | Progress: (16/20) | 13.75 s
+[Task  7/25]  Current/Best:   14.99/  19.03 GFLOPS | Progress: (20/20) | 15.92 s Done.
 
 [Task  8/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  8/25]  Current/Best:    9.05/  16.66 GFLOPS | Progress: (4/20) | 5.53 s
-[Task  8/25]  Current/Best:    8.12/  16.66 GFLOPS | Progress: (8/20) | 8.94 s
-[Task  8/25]  Current/Best:    8.68/  16.66 GFLOPS | Progress: (12/20) | 13.86 s
-[Task  8/25]  Current/Best:   16.82/  16.82 GFLOPS | Progress: (16/20) | 16.03 s
-[Task  8/25]  Current/Best:    5.17/  16.82 GFLOPS | Progress: (20/20) | 20.09 s Done.
+[Task  8/25]  Current/Best:   16.79/  16.79 GFLOPS | Progress: (4/20) | 4.90 s
+[Task  8/25]  Current/Best:    5.93/  17.00 GFLOPS | Progress: (8/20) | 10.98 s
+[Task  8/25]  Current/Best:   14.53/  21.30 GFLOPS | Progress: (12/20) | 13.75 s
+[Task  8/25]  Current/Best:    6.01/  21.30 GFLOPS | Progress: (16/20) | 23.55 s
+[Task  8/25]  Current/Best:    9.68/  21.30 GFLOPS | Progress: (20/20) | 26.87 s Done.
 
 [Task  9/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  9/25]  Current/Best:    8.27/  16.49 GFLOPS | Progress: (4/20) | 6.57 s
-[Task  9/25]  Current/Best:    8.67/  16.49 GFLOPS | Progress: (8/20) | 14.62 s
-[Task  9/25]  Current/Best:   11.92/  21.62 GFLOPS | Progress: (12/20) | 18.17 s
-[Task  9/25]  Current/Best:   18.67/  21.81 GFLOPS | Progress: (16/20) | 21.51 s
-[Task  9/25]  Current/Best:   10.97/  21.81 GFLOPS | Progress: (20/20) | 27.27 s Done.
+[Task  9/25]  Current/Best:   10.16/  19.68 GFLOPS | Progress: (4/20) | 7.93 s
+[Task  9/25]  Current/Best:   15.15/  19.68 GFLOPS | Progress: (8/20) | 10.18 s
+[Task  9/25]  Current/Best:   12.62/  19.68 GFLOPS | Progress: (12/20) | 13.64 s
+[Task  9/25]  Current/Best:   12.22/  19.68 GFLOPS | Progress: (16/20) | 20.07 s
+[Task  9/25]  Current/Best:   19.34/  19.68 GFLOPS | Progress: (20/20) | 21.93 s Done.
 
 [Task 10/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25]  Current/Best:   18.67/  18.67 GFLOPS | Progress: (4/20) | 3.52 s
-[Task 10/25]  Current/Best:   10.04/  18.67 GFLOPS | Progress: (8/20) | 5.73 s
-[Task 10/25]  Current/Best:   10.89/  21.60 GFLOPS | Progress: (12/20) | 8.08 s
-[Task 10/25]  Current/Best:   10.22/  21.60 GFLOPS | Progress: (16/20) | 10.71 s
-[Task 10/25]  Current/Best:    7.90/  21.60 GFLOPS | Progress: (20/20) | 13.26 s Done.
+[Task 10/25]  Current/Best:   16.62/  18.08 GFLOPS | Progress: (4/20) | 4.84 s
+[Task 10/25]  Current/Best:   14.00/  18.08 GFLOPS | Progress: (8/20) | 7.48 s
+[Task 10/25]  Current/Best:   21.25/  21.25 GFLOPS | Progress: (12/20) | 9.55 s
+[Task 10/25]  Current/Best:   13.45/  21.25 GFLOPS | Progress: (16/20) | 11.82 s
+[Task 10/25]  Current/Best:   11.19/  21.25 GFLOPS | Progress: (20/20) | 14.12 s Done.
 
 [Task 11/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25]  Current/Best:   11.09/  21.19 GFLOPS | Progress: (4/20) | 4.25 s
-[Task 11/25]  Current/Best:   11.26/  21.19 GFLOPS | Progress: (8/20) | 7.12 s
-[Task 11/25]  Current/Best:   11.00/  22.11 GFLOPS | Progress: (12/20) | 10.47 s
-[Task 11/25]  Current/Best:   21.58/  22.11 GFLOPS | Progress: (16/20) | 14.20 s
-[Task 11/25]  Current/Best:   18.65/  22.11 GFLOPS | Progress: (20/20) | 16.86 s Done.
+[Task 11/25]  Current/Best:   11.53/  18.04 GFLOPS | Progress: (4/20) | 4.15 s
+[Task 11/25]  Current/Best:   15.26/  18.04 GFLOPS | Progress: (8/20) | 6.57 s
+[Task 11/25]  Current/Best:   11.73/  19.95 GFLOPS | Progress: (12/20) | 9.03 s
+[Task 11/25]  Current/Best:   17.75/  19.95 GFLOPS | Progress: (16/20) | 11.32 s
+[Task 11/25]  Current/Best:    7.81/  20.24 GFLOPS | Progress: (20/20) | 13.51 s Done.
 
 [Task 12/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25]  Current/Best:    7.39/  14.19 GFLOPS | Progress: (4/20) | 7.24 s
-[Task 12/25]  Current/Best:    9.13/  19.32 GFLOPS | Progress: (8/20) | 10.19 s
-[Task 12/25]  Current/Best:   14.48/  21.41 GFLOPS | Progress: (12/20) | 13.42 s
-[Task 12/25]  Current/Best:   11.43/  21.41 GFLOPS | Progress: (16/20) | 15.78 s
-[Task 12/25]  Current/Best:   22.45/  22.45 GFLOPS | Progress: (20/20) | 18.27 s Done.
+[Task 12/25]  Current/Best:   14.96/  18.52 GFLOPS | Progress: (4/20) | 5.28 s
+[Task 12/25]  Current/Best:    6.40/  18.52 GFLOPS | Progress: (8/20) | 7.99 s
+[Task 12/25]  Current/Best:   10.06/  19.63 GFLOPS | Progress: (12/20) | 9.95 s
+[Task 12/25]  Current/Best:   14.26/  19.63 GFLOPS | Progress: (16/20) | 12.67 s
+[Task 12/25]  Current/Best:   14.26/  19.63 GFLOPS | Progress: (20/20) | 18.29 s Done.
 
 [Task 13/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25]  Current/Best:   18.44/  21.98 GFLOPS | Progress: (4/20) | 5.49 s
-[Task 13/25]  Current/Best:   12.44/  21.98 GFLOPS | Progress: (8/20) | 7.77 s
-[Task 13/25]  Current/Best:   23.01/  23.01 GFLOPS | Progress: (12/20) | 10.98 s
-[Task 13/25]  Current/Best:    9.27/  23.01 GFLOPS | Progress: (16/20) | 14.93 s
-[Task 13/25]  Current/Best:   17.38/  23.01 GFLOPS | Progress: (20/20) | 17.86 s Done.
+[Task 13/25]  Current/Best:    8.17/  18.73 GFLOPS | Progress: (4/20) | 4.38 s
+[Task 13/25]  Current/Best:   12.13/  18.73 GFLOPS | Progress: (8/20) | 7.13 s
+[Task 13/25]  Current/Best:   12.15/  21.24 GFLOPS | Progress: (12/20) | 9.80 s
+[Task 13/25]  Current/Best:    9.43/  21.24 GFLOPS | Progress: (16/20) | 12.24 s
+[Task 13/25]  Current/Best:   18.23/  21.24 GFLOPS | Progress: (20/20) | 15.92 s Done.
 
 [Task 14/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25]  Current/Best:   14.00/  17.87 GFLOPS | Progress: (4/20) | 5.03 s
-[Task 14/25]  Current/Best:    9.01/  18.29 GFLOPS | Progress: (8/20) | 8.95 s
-[Task 14/25]  Current/Best:   10.73/  18.29 GFLOPS | Progress: (12/20) | 12.23 s
-[Task 14/25]  Current/Best:   12.82/  18.29 GFLOPS | Progress: (16/20) | 15.85 s
-[Task 14/25]  Current/Best:   10.89/  18.29 GFLOPS | Progress: (20/20) | 18.61 s
+[Task 14/25]  Current/Best:    6.88/  11.63 GFLOPS | Progress: (4/20) | 4.71 s
+[Task 14/25]  Current/Best:   17.84/  17.84 GFLOPS | Progress: (8/20) | 7.99 s
+[Task 14/25]  Current/Best:   18.97/  18.97 GFLOPS | Progress: (12/20) | 10.63 s
+[Task 14/25]  Current/Best:   11.48/  18.97 GFLOPS | Progress: (16/20) | 12.85 s
+[Task 14/25]  Current/Best:   10.74/  18.97 GFLOPS | Progress: (20/20) | 17.51 s
 [Task 15/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25]  Current/Best:    8.50/  18.22 GFLOPS | Progress: (4/20) | 3.50 s
-[Task 15/25]  Current/Best:    9.60/  18.22 GFLOPS | Progress: (8/20) | 7.32 s
-[Task 15/25]  Current/Best:   15.88/  18.22 GFLOPS | Progress: (12/20) | 10.10 s
-[Task 15/25]  Current/Best:   22.26/  22.26 GFLOPS | Progress: (16/20) | 15.06 s
-[Task 15/25]  Current/Best:   14.30/  22.26 GFLOPS | Progress: (20/20) | 17.35 s
+[Task 15/25]  Current/Best:   18.38/  18.38 GFLOPS | Progress: (4/20) | 8.90 s
+[Task 15/25]  Current/Best:   13.06/  18.38 GFLOPS | Progress: (8/20) | 12.97 s
+[Task 15/25]  Current/Best:   12.28/  18.38 GFLOPS | Progress: (12/20) | 14.50 s
+[Task 15/25]  Current/Best:   15.46/  18.38 GFLOPS | Progress: (16/20) | 19.66 s
+[Task 15/25]  Current/Best:   17.83/  19.40 GFLOPS | Progress: (20/20) | 21.24 s
 [Task 16/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25]  Current/Best:    9.55/  23.28 GFLOPS | Progress: (4/20) | 4.21 s
-[Task 16/25]  Current/Best:   15.37/  23.28 GFLOPS | Progress: (8/20) | 6.28 s
-[Task 16/25]  Current/Best:   17.33/  23.28 GFLOPS | Progress: (12/20) | 8.48 s
-[Task 16/25]  Current/Best:   14.76/  23.28 GFLOPS | Progress: (16/20) | 10.03 s
-[Task 16/25]  Current/Best:   13.86/  23.28 GFLOPS | Progress: (20/20) | 11.78 s Done.
-
-[Task 17/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25]  Current/Best:   17.62/  17.62 GFLOPS | Progress: (4/20) | 4.75 s
-[Task 17/25]  Current/Best:   17.49/  17.62 GFLOPS | Progress: (8/20) | 8.28 s Done.
+[Task 16/25]  Current/Best:   17.69/  17.69 GFLOPS | Progress: (4/20) | 3.42 s Done.
  Done.
 
-[Task 17/25]  Current/Best:   17.71/  21.21 GFLOPS | Progress: (12/20) | 10.90 s
-[Task 17/25]  Current/Best:   12.72/  21.21 GFLOPS | Progress: (16/20) | 13.21 s
-[Task 17/25]  Current/Best:   16.49/  21.21 GFLOPS | Progress: (20/20) | 16.17 s Done.
+[Task 16/25]  Current/Best:    6.17/  17.69 GFLOPS | Progress: (8/20) | 5.70 s
+[Task 16/25]  Current/Best:   16.73/  18.02 GFLOPS | Progress: (12/20) | 7.70 s
+[Task 16/25]  Current/Best:    3.98/  20.10 GFLOPS | Progress: (16/20) | 9.54 s
+[Task 16/25]  Current/Best:    9.92/  20.10 GFLOPS | Progress: (20/20) | 12.43 s Done.
+
+[Task 17/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
+[Task 17/25]  Current/Best:   10.15/  17.82 GFLOPS | Progress: (4/20) | 5.34 s
+[Task 17/25]  Current/Best:   15.32/  17.82 GFLOPS | Progress: (8/20) | 8.23 s
+[Task 17/25]  Current/Best:   11.72/  17.82 GFLOPS | Progress: (12/20) | 13.15 s
+[Task 17/25]  Current/Best:   10.54/  17.82 GFLOPS | Progress: (16/20) | 16.55 s
+[Task 17/25]  Current/Best:   20.72/  23.97 GFLOPS | Progress: (20/20) | 18.68 s Done.
 
 [Task 18/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25]  Current/Best:   15.02/  17.64 GFLOPS | Progress: (4/20) | 4.05 s
-[Task 18/25]  Current/Best:    6.05/  17.64 GFLOPS | Progress: (8/20) | 14.75 s
-[Task 18/25]  Current/Best:   17.43/  19.72 GFLOPS | Progress: (12/20) | 17.17 s
-[Task 18/25]  Current/Best:    9.34/  19.72 GFLOPS | Progress: (16/20) | 20.29 s
-[Task 18/25]  Current/Best:    9.72/  19.72 GFLOPS | Progress: (20/20) | 25.46 s Done.
+[Task 18/25]  Current/Best:    6.76/   9.57 GFLOPS | Progress: (4/20) | 7.67 s
+[Task 18/25]  Current/Best:   11.69/  15.64 GFLOPS | Progress: (8/20) | 10.53 s
+[Task 18/25]  Current/Best:   17.27/  19.16 GFLOPS | Progress: (12/20) | 15.37 s
+[Task 18/25]  Current/Best:   10.58/  19.69 GFLOPS | Progress: (16/20) | 18.42 s
+[Task 18/25]  Current/Best:    9.24/  19.69 GFLOPS | Progress: (20/20) | 23.12 s Done.
 
 [Task 19/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25]  Current/Best:   10.44/  12.15 GFLOPS | Progress: (4/20) | 9.70 s
-[Task 19/25]  Current/Best:    2.69/  16.99 GFLOPS | Progress: (8/20) | 13.18 s
-[Task 19/25]  Current/Best:    6.16/  18.42 GFLOPS | Progress: (12/20) | 16.65 s
-[Task 19/25]  Current/Best:    2.69/  18.42 GFLOPS | Progress: (16/20) | 21.02 s
-[Task 19/25]  Current/Best:    1.55/  22.59 GFLOPS | Progress: (20/20) | 25.77 s Done.
+[Task 19/25]  Current/Best:    9.79/  14.78 GFLOPS | Progress: (4/20) | 5.02 s
+[Task 19/25]  Current/Best:   10.89/  20.56 GFLOPS | Progress: (8/20) | 9.88 s
+[Task 19/25]  Current/Best:    8.45/  20.56 GFLOPS | Progress: (12/20) | 13.58 s
+[Task 19/25]  Current/Best:   11.27/  20.56 GFLOPS | Progress: (16/20) | 16.23 s
+[Task 19/25]  Current/Best:   10.25/  20.56 GFLOPS | Progress: (20/20) | 20.09 s Done.
 
 [Task 20/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25]  Current/Best:   15.94/  17.24 GFLOPS | Progress: (4/20) | 4.57 s
-[Task 20/25]  Current/Best:   16.26/  17.24 GFLOPS | Progress: (8/20) | 10.06 s
-[Task 20/25]  Current/Best:   11.49/  17.24 GFLOPS | Progress: (12/20) | 12.50 s
-[Task 20/25]  Current/Best:   17.42/  17.42 GFLOPS | Progress: (16/20) | 15.36 s
-[Task 20/25]  Current/Best:    9.11/  17.42 GFLOPS | Progress: (20/20) | 18.40 s
+[Task 20/25]  Current/Best:   14.27/  17.93 GFLOPS | Progress: (4/20) | 4.17 s
+[Task 20/25]  Current/Best:    7.42/  18.41 GFLOPS | Progress: (8/20) | 7.95 s
+[Task 20/25]  Current/Best:    7.81/  18.41 GFLOPS | Progress: (12/20) | 10.12 s
+[Task 20/25]  Current/Best:    9.45/  18.41 GFLOPS | Progress: (16/20) | 14.65 s
+[Task 20/25]  Current/Best:    7.88/  18.41 GFLOPS | Progress: (20/20) | 17.96 s
 [Task 21/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25]  Current/Best:    2.77/  16.67 GFLOPS | Progress: (4/20) | 3.70 s
-[Task 21/25]  Current/Best:    5.29/  18.96 GFLOPS | Progress: (8/20) | 8.05 s
-[Task 21/25]  Current/Best:   17.32/  18.96 GFLOPS | Progress: (12/20) | 10.14 s
-[Task 21/25]  Current/Best:   10.86/  18.96 GFLOPS | Progress: (16/20) | 12.29 s
-[Task 21/25]  Current/Best:   16.04/  18.96 GFLOPS | Progress: (20/20) | 14.19 s
-[Task 22/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
- Done.
-
-[Task 22/25]  Current/Best:   10.69/  15.10 GFLOPS | Progress: (4/20) | 5.34 s
-[Task 22/25]  Current/Best:   11.55/  17.98 GFLOPS | Progress: (8/20) | 7.68 s
-[Task 22/25]  Current/Best:    6.82/  17.98 GFLOPS | Progress: (12/20) | 11.65 s
-[Task 22/25]  Current/Best:   10.45/  17.98 GFLOPS | Progress: (16/20) | 13.53 s
-[Task 22/25]  Current/Best:    2.62/  18.14 GFLOPS | Progress: (20/20) | 15.68 s Done.
+[Task 21/25]  Current/Best:   14.31/  17.27 GFLOPS | Progress: (4/20) | 3.35 s
+[Task 21/25]  Current/Best:   13.90/  18.39 GFLOPS | Progress: (8/20) | 6.12 s
+[Task 21/25]  Current/Best:   16.55/  18.39 GFLOPS | Progress: (12/20) | 8.62 s
+[Task 21/25]  Current/Best:   12.48/  18.39 GFLOPS | Progress: (16/20) | 10.60 s
+[Task 21/25]  Current/Best:    7.43/  18.39 GFLOPS | Progress: (20/20) | 13.50 s
+[Task 22/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
+[Task 22/25]  Current/Best:   19.35/  19.35 GFLOPS | Progress: (4/20) | 4.24 s
+[Task 22/25]  Current/Best:   16.57/  19.35 GFLOPS | Progress: (8/20) | 8.80 s
+[Task 22/25]  Current/Best:    6.60/  19.35 GFLOPS | Progress: (12/20) | 10.89 s
+[Task 22/25]  Current/Best:   21.00/  21.00 GFLOPS | Progress: (16/20) | 12.61 s
+[Task 22/25]  Current/Best:    7.65/  21.00 GFLOPS | Progress: (20/20) | 15.21 s Done.
 
 [Task 23/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25]  Current/Best:   19.05/  19.77 GFLOPS | Progress: (4/20) | 4.12 s
-[Task 23/25]  Current/Best:   18.32/  19.77 GFLOPS | Progress: (8/20) | 7.37 s
-[Task 23/25]  Current/Best:   18.92/  19.77 GFLOPS | Progress: (12/20) | 11.31 s
-[Task 23/25]  Current/Best:    5.23/  19.77 GFLOPS | Progress: (16/20) | 15.25 s
-[Task 23/25]  Current/Best:   17.88/  19.77 GFLOPS | Progress: (20/20) | 20.37 s Done.
+[Task 23/25]  Current/Best:   10.50/  19.70 GFLOPS | Progress: (4/20) | 5.44 s
+[Task 23/25]  Current/Best:    1.55/  19.88 GFLOPS | Progress: (8/20) | 12.29 s
+[Task 23/25]  Current/Best:    6.52/  19.88 GFLOPS | Progress: (12/20) | 18.45 s
+[Task 23/25]  Current/Best:   18.14/  19.88 GFLOPS | Progress: (16/20) | 21.13 s
+[Task 23/25]  Current/Best:    6.15/  19.88 GFLOPS | Progress: (20/20) | 24.07 s Done.
 
 [Task 24/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25]  Current/Best:    2.92/   7.98 GFLOPS | Progress: (4/20) | 12.85 s
-[Task 24/25]  Current/Best:    3.00/   8.54 GFLOPS | Progress: (8/20) | 17.42 s
-[Task 24/25]  Current/Best:    2.50/   8.54 GFLOPS | Progress: (12/20) | 28.10 s
-[Task 24/25]  Current/Best:    2.97/   8.54 GFLOPS | Progress: (16/20) | 39.07 s
-[Task 24/25]  Current/Best:    4.63/   8.54 GFLOPS | Progress: (20/20) | 46.11 s
-[Task 25/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
-
-[Task 25/25]  Current/Best:    5.28/   5.28 GFLOPS | Progress: (4/20) | 13.37 s
-[Task 25/25]  Current/Best:    5.77/   5.77 GFLOPS | Progress: (8/20) | 25.27 s
-[Task 25/25]  Current/Best:    5.72/   5.77 GFLOPS | Progress: (12/20) | 27.44 s
-[Task 25/25]  Current/Best:    1.55/   7.85 GFLOPS | Progress: (16/20) | 38.43 s
-[Task 25/25]  Current/Best:    8.06/   8.06 GFLOPS | Progress: (20/20) | 43.15 s
+[Task 24/25]  Current/Best:    2.44/   7.16 GFLOPS | Progress: (4/20) | 4.94 s
+[Task 24/25]  Current/Best:    3.82/   7.16 GFLOPS | Progress: (8/20) | 11.80 s Done.
+ Done.
+
+[Task 24/25]  Current/Best:    5.84/   7.16 GFLOPS | Progress: (12/20) | 22.75 s
+[Task 24/25]  Current/Best:    1.89/   7.16 GFLOPS | Progress: (16/20) | 33.71 s
+[Task 24/25]  Current/Best:    5.98/   7.16 GFLOPS | Progress: (20/20) | 44.09 s
+[Task 25/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
+[Task 25/25]  Current/Best:    5.75/   6.71 GFLOPS | Progress: (4/20) | 4.42 s
+[Task 25/25]  Current/Best:    1.53/   6.71 GFLOPS | Progress: (8/20) | 15.41 s
+[Task 25/25]  Current/Best:    3.04/   9.69 GFLOPS | Progress: (12/20) | 20.57 s
+[Task 25/25]  Current/Best:    6.00/   9.69 GFLOPS | Progress: (16/20) | 31.53 s
+[Task 25/25]  Current/Best:    5.80/   9.69 GFLOPS | Progress: (20/20) | 42.50 s
 </pre></div>
 </div>
 <p>The output from this tuning process will look something like this:</p>
@@ -943,8 +942,8 @@ model using optimized operators to speed up our computations.</p>
     <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;class=&#39;</span><span class="si">%s</span><span class="s2">&#39; with probability=</span><span class="si">%f</span><span class="s2">&quot;</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#list" title="builtins.list" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">labels</span></a [...]
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class=&#39;n02123045 tabby, tabby cat&#39; with probability=0.621104
-class=&#39;n02123159 tiger cat&#39; with probability=0.356378
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class=&#39;n02123045 tabby, tabby cat&#39; with probability=0.621102
+class=&#39;n02123159 tiger cat&#39; with probability=0.356380
 class=&#39;n02124075 Egyptian cat&#39; with probability=0.019712
 class=&#39;n02129604 tiger, Panthera tigris&#39; with probability=0.001215
 class=&#39;n04040759 radiator&#39; with probability=0.000262
@@ -981,8 +980,8 @@ improvement in comparing the optimized model to the unoptimized model.</p>
 <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;unoptimized: </span><span class="si">%s</span><span class="s2">&quot;</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">))</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {&#39;mean&#39;: 415.98896696998054, &#39;median&#39;: 415.9302147499602, &#39;std&#39;: 3.422307767796741}
-unoptimized: {&#39;mean&#39;: 517.6268569099921, &#39;median&#39;: 517.4762197500058, &#39;std&#39;: 2.3963316360720026}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {&#39;mean&#39;: 427.6049398500004, &#39;median&#39;: 427.5632347000055, &#39;std&#39;: 1.87073181743225}
+unoptimized: {&#39;mean&#39;: 518.0414347700003, &#39;median&#39;: 518.4623476000013, &#39;std&#39;: 2.0786998699138803}
 </pre></div>
 </div>
 </div>
@@ -996,7 +995,7 @@ models.</p>
 <p>Here we presented a simple example using ResNet-50 v2 locally. However, TVM
 supports many more features including cross-compilation, remote execution and
 profiling/benchmarking.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 12 minutes  14.094 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 12 minutes  0.009 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 af45111149..e6ad36c86e 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -538,7 +538,7 @@ 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>1.272e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.469e-07 secs/op
 </pre></div>
 </div>
 </div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index cef6b483a5..ee7a760c93 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -508,7 +508,7 @@ class Module:
 <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, 0x218124c0)), stage(b, placeholder(b, 0x57cd640)), stage(T_add, compute(T_add, body=[a[ax0, ax1, ax2] + b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), &quot;DataPar&quot;, &quot;&quot;), T.iter_var(ax1, T.Range(0, 10), &quot;DataPar&quot;, &quot;&quot;), T.iter_var(ax2, T.Range(0, 10), &quot;DataPar&quot;, &quot;&quot;)], reduce_axis=[], tag=broadcast, attrs [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x9fb71c0)), stage(b, placeholder(b, 0xe222810)), stage(T_add, compute(T_add, body=[a[ax0, ax1, ax2] + b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), &quot;DataPar&quot;, &quot;&quot;), T.iter_var(ax1, T.Range(0, 10), &quot;DataPar&quot;, &quot;&quot;), T.iter_var(ax2, T.Range(0, 10), &quot;DataPar&quot;, &quot;&quot;)], reduce_axis=[], tag=broadcast, attrs= [...]
 </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 3efe9be219..23547e7f1d 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -340,7 +340,7 @@
             
   <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>15:38.310</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>15:21.533</strong> total execution time for <strong>tutorial</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 83%" />
@@ -349,35 +349,35 @@
 </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>12:14.094</p></td>
+<td><p>12:00.009</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <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>01:14.063</p></td>
+<td><p>01:14.570</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <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>01:00.772</p></td>
+<td><p>01:01.082</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>00:35.961</p></td>
+<td><p>00:35.831</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>00:31.771</p></td>
+<td><p>00:27.583</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
-<tr class="row-even"><td><p><a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></td>
-<td><p>00:00.846</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></td>
+<td><p>00:01.446</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></td>
-<td><p>00:00.618</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></td>
+<td><p>00:00.833</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>00:00.184</p></td>
+<td><p>00:00.179</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><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>
@@ -388,11 +388,11 @@
 <td><p>00:00.000</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></td>
+<tr class="row-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>
 <td><p>00:00.000</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
-<tr class="row-even"><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>
+<tr class="row-even"><td><p><a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></td>
 <td><p>00:00.000</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index 5a30ea28bf..46d12e43c2 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -605,7 +605,7 @@ compile and run this new schedule with the parallel operation applied:</p>
 <span class="n">evaluate_addition</span><span class="p">(</span><span class="n">fadd_parallel</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;parallel&quot;</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.h [...]
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallel: 0.000007
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallel: 0.000008
 </pre></div>
 </div>
 </div>
@@ -681,10 +681,10 @@ class Module:
 </pre></div>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator                  Timing             Performance
-   numpy    7.056659997033421e-06                    1.0
-   naive              6.7006e-06      0.9495427019038601
-parallel    6.959200000000001e-06     0.9861889339893957
-  vector    2.4585599999999997e-05    3.4840278560020805
+   numpy    7.388540000192734e-06                    1.0
+   naive    6.653999999999999e-06     0.9005838771701076
+parallel              8.0759e-06      1.0930305581061124
+  vector    2.4604200000000004e-05    3.3300489676388287
 </pre></div>
 </div>
 <div class="admonition-code-specialization admonition">
@@ -1000,7 +1000,7 @@ 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: 0.018855
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018827
 </pre></div>
 </div>
 <p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -1041,7 +1041,7 @@ optimizations.</p>
 <span class="n">evaluate_operation</span><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">s</span></a><span class="p">,</span> <span class="p">[</span><a href="../reference/api/python/te.html#tvm.te.Tensor" title="tvm.te.Tensor" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance [...]
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.346853
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.385970
 </pre></div>
 </div>
 <p>Let’s take a look at the intermediate representation of the operator and
@@ -1105,7 +1105,7 @@ schedule.</p>
 <span class="n">evaluate_operation</span><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">s</span></a><span class="p">,</span> <span class="p">[</span><a href="../reference/api/python/te.html#tvm.te.Tensor" title="tvm.te.Tensor" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance [...]
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.316665
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.309784
 </pre></div>
 </div>
 <p>By reordering the computation to take advantage of caching, you should see a
@@ -1154,7 +1154,7 @@ already cache friendly from our previous optimizations.</p>
 <span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.360209
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.345993
 @I.ir_module
 class Module:
     @T.prim_func
@@ -1203,7 +1203,7 @@ more cache friendly.</p>
 <span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.120309
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.122252
 @I.ir_module
 class Module:
     @T.prim_func
@@ -1273,7 +1273,7 @@ optimized schedule.</p>
 <span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.107902
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.110152
 @I.ir_module
 class Module:
     @T.prim_func
@@ -1339,7 +1339,7 @@ to `C</cite> when all the block results are ready.</p>
 <span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.111348
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.111498
 @I.ir_module
 class Module:
     @T.prim_func
@@ -1396,7 +1396,7 @@ of thread-level parallelization.</p>
 <span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.146428
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.146479
 @I.ir_module
 class Module:
     @T.prim_func
@@ -1449,13 +1449,13 @@ 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      3.3468527762999996                     1.0
-        blocking     0.31666541800000003     0.09461587920520328
-   vectorization            0.3602094293     0.10762631444404835
-loop permutation     0.12030926830000002    0.035946985523816165
-   array packing            0.1079019317     0.03223982018691821
-   block caching            0.1113483064    0.033269556159891016
- parallelization            0.1464283433     0.04375105601802985
+            none      3.3859701759000003                     1.0
+        blocking            0.3097840192     0.09149047484378935
+   vectorization     0.34599302499999995     0.10218430967367692
+loop permutation     0.12225169450000002     0.03610536660072772
+   array packing              0.11015217     0.03253193745887654
+   block caching            0.1114983212     0.03292950481182648
+ parallelization            0.1464793376     0.04326066976093946
 </pre></div>
 </div>
 <p>Note that the outputs on the web page reflect the running times on a
@@ -1487,7 +1487,7 @@ 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  0.772 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  1.082 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>