You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by tq...@apache.org on 2022/11/16 18:38:43 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@44ed06ac9f019f9f06608504c3382d0905b6d5a2)

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 a79767c1fc deploying docs (apache/tvm@44ed06ac9f019f9f06608504c3382d0905b6d5a2)
a79767c1fc is described below

commit a79767c1fcaeaa9dca62e23cb89d3d9c847efd3b
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Wed Nov 16 18:38:37 2022 +0000

    deploying docs (apache/tvm@44ed06ac9f019f9f06608504c3382d0905b6d5a2)
---
 docs/_images/sphx_glr_micro_train_001.png          |  Bin 327199 -> 337505 bytes
 docs/_images/sphx_glr_micro_train_thumb.png        |  Bin 22934 -> 23675 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_android.rst.txt  |    2 +-
 .../deploy_object_detection_pytorch.rst.txt        |    4 +-
 .../deploy_models/deploy_prequantized.rst.txt      |    6 +-
 .../deploy_prequantized_tflite.rst.txt             |    4 +-
 .../how_to/deploy_models/deploy_quantized.rst.txt  |    2 +-
 .../deploy_models/deploy_ssd_gluoncv.rst.txt       |    4 +-
 .../deploy_models/sg_execution_times.rst.txt       |   18 +-
 .../extend_tvm/bring_your_own_datatypes.rst.txt    |    2 +-
 .../how_to/extend_tvm/sg_execution_times.rst.txt   |    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                 | 1270 ++++++--------------
 .../tune_network_cuda.rst.txt                      |    4 +-
 .../tune_network_x86.rst.txt                       |    4 +-
 .../tune_sparse_x86.rst.txt                        |   31 +-
 .../tune_with_autotvm/sg_execution_times.rst.txt   |    6 +-
 .../tune_with_autotvm/tune_conv2d_cuda.rst.txt     |  434 ++++++-
 .../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  |   10 +-
 .../work_with_relay/sg_execution_times.rst.txt     |    8 +-
 .../how_to/work_with_schedules/intrin_math.rst.txt |    2 +-
 .../work_with_schedules/sg_execution_times.rst.txt |   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     |   11 +-
 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  |   18 +-
 .../tutorial/tensor_expr_get_started.rst.txt       |   44 +-
 docs/commit_hash                                   |    2 +-
 docs/how_to/compile_models/from_darknet.html       |    2 +-
 docs/how_to/compile_models/from_keras.html         |    2 +-
 docs/how_to/compile_models/from_mxnet.html         |    2 +-
 docs/how_to/compile_models/from_oneflow.html       |   15 +-
 docs/how_to/compile_models/from_pytorch.html       |   15 +-
 docs/how_to/compile_models/from_tensorflow.html    |    2 +-
 docs/how_to/compile_models/sg_execution_times.html |   26 +-
 .../deploy_models/deploy_model_on_android.html     |    2 +-
 .../deploy_object_detection_pytorch.html           |   53 +-
 docs/how_to/deploy_models/deploy_prequantized.html |    9 +-
 .../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  |   18 +-
 .../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                    | 1269 ++++++-------------
 .../tune_with_autoscheduler/tune_network_cuda.html |    4 +-
 .../tune_with_autoscheduler/tune_network_x86.html  |    4 +-
 .../tune_with_autoscheduler/tune_sparse_x86.html   |   31 +-
 .../tune_with_autotvm/sg_execution_times.html      |    6 +-
 .../how_to/tune_with_autotvm/tune_conv2d_cuda.html |  434 ++++++-
 docs/how_to/work_with_microtvm/micro_autotune.html |   16 +-
 docs/how_to/work_with_microtvm/micro_pytorch.html  |    4 +-
 docs/how_to/work_with_microtvm/micro_train.html    |   16 +-
 .../work_with_microtvm/sg_execution_times.html     |   10 +-
 .../how_to/work_with_relay/sg_execution_times.html |    8 +-
 docs/how_to/work_with_schedules/intrin_math.html   |    2 +-
 .../work_with_schedules/sg_execution_times.html    |   16 +-
 docs/how_to/work_with_schedules/tensorize.html     |    2 +-
 docs/reference/api/python/auto_scheduler.html      |    4 +-
 .../api/typedoc/classes/bytestreamreader.html      |   12 +-
 .../api/typedoc/classes/cachedcallstack.html       |   34 +-
 docs/reference/api/typedoc/classes/dldatatype.html |   12 +-
 docs/reference/api/typedoc/classes/dldevice.html   |   10 +-
 .../reference/api/typedoc/classes/environment.html |   12 +-
 docs/reference/api/typedoc/classes/ffilibrary.html |   20 +-
 .../api/typedoc/classes/graphexecutor.html         |   16 +-
 docs/reference/api/typedoc/classes/instance.html   |   40 +-
 docs/reference/api/typedoc/classes/memory.html     |   34 +-
 docs/reference/api/typedoc/classes/module.html     |   10 +-
 docs/reference/api/typedoc/classes/ndarray.html    |   22 +-
 .../api/typedoc/classes/packedfunccell.html        |    6 +-
 docs/reference/api/typedoc/classes/rpcserver.html  |   14 +-
 docs/reference/api/typedoc/classes/scalar.html     |    6 +-
 .../api/typedoc/classes/webgpucontext.html         |   12 +-
 docs/reference/api/typedoc/enums/argtypecode.html  |   30 +-
 .../api/typedoc/enums/aynccallbackcode.html        |    4 +-
 .../api/typedoc/enums/dldatatypecode.html          |    8 +-
 .../api/typedoc/enums/rpcserverstate.html          |   12 +-
 docs/reference/api/typedoc/enums/sizeof.html       |   18 +-
 docs/reference/api/typedoc/index.html              |  112 +-
 .../api/typedoc/interfaces/disposable.html         |    2 +-
 .../api/typedoc/interfaces/functioninfo.html       |    6 +-
 .../api/typedoc/interfaces/libraryprovider.html    |    4 +-
 docs/searchindex.js                                |    2 +-
 .../vta/tutorials/autotvm/sg_execution_times.html  |    4 +-
 .../tutorials/frontend/deploy_classification.html  |    2 +-
 .../vta/tutorials/frontend/deploy_detection.html   |    2 +-
 .../vta/tutorials/frontend/sg_execution_times.html |    6 +-
 .../vta/tutorials/optimize/sg_execution_times.html |    6 +-
 docs/topic/vta/tutorials/sg_execution_times.html   |    6 +-
 docs/tutorial/auto_scheduler_matmul_x86.html       |    7 +-
 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              |   18 +-
 docs/tutorial/tensor_expr_get_started.html         |   44 +-
 127 files changed, 2364 insertions(+), 2719 deletions(-)

diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index 9acba7fd3b..cdece017f1 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 fb0f49ab60..3ea3b2a601 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 7a1b9de483..d0835e1320 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -315,7 +315,7 @@ The process is no different from other examples.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  13.629 seconds)
+   **Total running time of the script:** ( 1 minutes  13.405 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 35ff6fe2ee..595ac3a7a0 100644
--- a/docs/_sources/how_to/compile_models/from_keras.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_keras.rst.txt
@@ -228,7 +228,7 @@ Look up prediction top 1 index in 1000 class synset.
  .. code-block:: none
 
     Relay top-1 id: 285, class name: Egyptian cat
-
    1/1 [==============================] - ETA: 0s
    1/1 [==============================] - 1s 958ms/step
+
    1/1 [==============================] - ETA: 0s
    1/1 [==============================] - 1s 964ms/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 cd89d79ae4..f110a29d18 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -115,7 +115,7 @@ In this section, we download a pretrained imagenet model and classify an image.
 
  .. code-block:: none
 
-    Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip6172288d-0a35-409b-9577-c9b5f252dbdd from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+    Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip6703bb06-6b2d-4042-9067-f67e09bca4e5 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 617b4fbb2a..641e251484 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -116,7 +116,7 @@ Load a pretrained OneFlow model and save model
  .. code-block:: none
 
     Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
      0%|          | 0.00/41.5M [00:00<?, ?B/s]
     15%|#5        | 6.33M/41.5M [00:00<00:00, 47.2MB/s]
     26%|##6       | 10.8M/41.5M [00:00<00:00, 38.8MB/s]
     39%|###8      | 16.0M/41.5M [00:00<00:00, 39.6MB/s]
     58%|#####7    | 24.0M/41.5M [00:00<00:00, 38.3MB/s]
     77%|#######7  | 32.0M/41.5M [00:00<00:00, 43.5MB/s]
     87%|########7 | 36.2M/41.5M [00:00<00:00, 43.4MB/s]
    100%|##########| 41.5M/41.5M [00:00<00:00, 44.2MB/s]
+
      0%|          | 0.00/41.5M [00:00<?, ?B/s]
     15%|#5        | 6.33M/41.5M [00:00<00:00, 37.1MB/s]
     24%|##3       | 9.87M/41.5M [00:00<00:01, 29.5MB/s]
     39%|###8      | 16.0M/41.5M [00:00<00:00, 33.4MB/s]
     54%|#####3    | 22.3M/41.5M [00:00<00:00, 42.2MB/s]
     73%|#######3  | 30.3M/41.5M [00:00<00:00, 54.0MB/s]
     87%|########6 | 36.0M/41.5M [00:00<00:00, 45.8MB/s]
     98%|#########8| 40.8M/41.5M [00:01<00:00, 43.9MB/s]
    100%|##########| 41.5M/41.5M [00:01<00:00, 42.9MB/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 af9ad164a9..8cb00b1ff8 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -98,7 +98,7 @@ Load a pretrained PyTorch model
     /venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=ResNet18_Weights.IMAGENET1K_V1`. You can also use `weights=ResNet18_Weights.DEFAULT` to get the most up-to-date weights.
       warnings.warn(msg)
     Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
-
      0%|          | 0.00/44.7M [00:00<?, ?B/s]
     18%|#7        | 7.99M/44.7M [00:00<00:00, 39.7MB/s]
     36%|###5      | 16.0M/44.7M [00:00<00:00, 46.9MB/s]
     54%|#####3    | 24.1M/44.7M [00:00<00:00, 57.7MB/s]
     68%|######7   | 30.3M/44.7M [00:00<00:00, 47.9MB/s]
     79%|#######8  | 35.2M/44.7M [00:00<00:00, 43.7MB/s]
     90%|########9 | 40.0M/44.7M [00:00<00:00, 39.0MB/s]
    100%|##########| 44.7M/44.7M [00:01<00:00, 46.5MB/s]
+
      0%|          | 0.00/44.7M [00:00<?, ?B/s]
      6%|5         | 2.61M/44.7M [00:00<00:01, 22.4MB/s]
     18%|#7        | 7.99M/44.7M [00:00<00:01, 33.0MB/s]
     32%|###2      | 14.3M/44.7M [00:00<00:01, 31.7MB/s]
     39%|###8      | 17.3M/44.7M [00:00<00:00, 29.7MB/s]
     55%|#####4    | 24.5M/44.7M [00:00<00:00, 41.9MB/s]
     72%|#######1  | 32.0M/44.7M [00:00<00:00, 43.9MB/s]
     90%|########9 | 40.0M/44.7M [00:01<00:00, 42.2MB/s]
    100%|##########| 44.7M/44.7M [00:01<00:00, 42.3MB/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 a939096eef..e71f44fca2 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -416,7 +416,7 @@ Run the corresponding model on tensorflow
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  14.751 seconds)
+   **Total running time of the script:** ( 1 minutes  11.788 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 6af56a208a..3cd540c36a 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
 =================
-**06:02.125** total execution time for **how_to_compile_models** files:
+**05:52.981** total execution time for **how_to_compile_models** files:
 
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:14.751 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)       | 01:13.405 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)       | 01:13.629 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:11.788 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)         | 00:46.113 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)         | 00:46.658 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)       | 00:35.536 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)       | 00:33.757 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)           | 00:32.462 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)           | 00:30.473 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)         | 00:28.438 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)         | 00:26.763 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)         | 00:26.481 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)         | 00:25.790 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)       | 00:24.117 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)       | 00:23.270 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)           | 00:18.113 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)           | 00:18.636 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)             | 00:02.485 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)             | 00:02.439 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
index 9b6c488e3e..63a1f20153 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
@@ -433,7 +433,7 @@ Execute on TVM
     Evaluate inference time cost...
     Execution time summary:
      mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)  
-      16.0401      16.0527      16.2899      15.8806       0.1304   
+      16.2805      16.3876      16.6878      15.6962       0.3367   
                
 
 
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 501328ee2c..553acad3b6 100644
--- a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
@@ -127,7 +127,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
     /venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MaskRCNN_ResNet50_FPN_Weights.COCO_V1`. You can also use `weights=MaskRCNN_ResNet50_FPN_Weights.DEFAULT` to get the most up-to-date weights.
       warnings.warn(msg)
     Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
      0%|          | 0.00/170M [00:00<?, ?B/s]
      5%|4         | 7.99M/170M [00:00<00:02, 56.7MB/s]
      9%|9         | 16.0M/170M [00:00<00:02, 63.9MB/s]
     14%|#4        | 24.0M/170M [00:00<00:02, 53.8MB/s]
     19%|#8        | 32.0M/170M [00:00<00:02, 50.6MB/s]
     24%|##3       | 40.0M/170M [00:00<00:02, 55.8MB/s]
     27%|##7       | 46.3M/170M [00:00<00:02, 53.3MB/s]
     32%|###2      | 54.5M/170M [00:00<00:01, 61.5MB/s]
     36%|###5      | 60.7M/170M [00:01<00:01, 62.3MB/s]
     39%|###9      | 66.9M/170M [00:01<00:01, 62.1MB/s]
     43%|####2     | 73.0M/170M [00:01<00:01, 59.0MB/s]
     46%|####6     | 78.7M/170M [00:01<00:01, 59.2MB/s]
     51%|#####     | 86.3M/170M [00:01<00:01, 51.7MB/s]
     54%|#####3    | 91.5M/170M [00:01<00:01, 45.6MB/s]
     57%|#####6    | 96.1M/170M [00:01<00:01, 41.8MB/s]
     60%|######    | 102M/170M [00:02<00:01, 46.2MB/s] 
     64%|######4   | 109M/170M [00:02<00:01, 52.0MB/s]
     67%|######7   | 114M/170M [00:02<00:01, 48.1MB/s]
 
     71%|#######   | 120M/170M [00:02<00:01, 49.8MB/s]
     75%|#######5  | 128M/170M [00:02<00:00, 56.6MB/s]
     79%|#######9  | 134M/170M [00:02<00:00, 58.0MB/s]
     82%|########2 | 140M/170M [00:02<00:00, 53.5MB/s]
     86%|########5 | 146M/170M [00:02<00:00, 55.1MB/s]
     89%|########9 | 152M/170M [00:03<00:00, 46.7MB/s]
     94%|#########4| 160M/170M [00:03<00:00, 49.9MB/s]
    100%|##########| 170M/170M [00:03<00:00, 54.5MB/s]
+
      0%|          | 0.00/170M [00:00<?, ?B/s]
      5%|4         | 7.99M/170M [00:00<00:02, 61.7MB/s]
      8%|8         | 14.3M/170M [00:00<00:04, 36.6MB/s]
     11%|#         | 18.2M/170M [00:00<00:04, 37.0MB/s]
     13%|#3        | 22.3M/170M [00:00<00:05, 29.5MB/s]
     15%|#4        | 25.4M/170M [00:00<00:05, 29.7MB/s]
     21%|##        | 35.3M/170M [00:00<00:02, 48.6MB/s]
     24%|##3       | 40.7M/170M [00:01<00:02, 46.7MB/s]
     28%|##8       | 48.0M/170M [00:01<00:02, 48.3MB/s]
     33%|###2      | 56.0M/170M [00:01<00:02, 52.5MB/s]
     38%|###7      | 64.0M/170M [00:01<00:01, 58.0MB/s]
     42%|####2     | 72.0M/170M [00:01<00:01, 53.5MB/s]
     47%|####7     | 80.0M/170M [00:01<00:01, 53.3MB/s]
     51%|#####     | 86.3M/170M [00:01<00:01, 56.0MB/s]
     54%|#####4    | 91.9M/170M [00:01<00:01, 56.0MB/s]
     58%|#####8    | 98.6M/170M [00:02<00:01, 59.6MB/s]
     62%|######1   | 104M/170M [00:02<00:01, 54.0MB/s] 
     68%|######7   | 115M/170M [00:02<00:00, 68.1MB/s
 ]
     72%|#######1  | 122M/170M [00:02<00:00, 66.7MB/s]
     76%|#######5  | 128M/170M [00:02<00:00, 64.8MB/s]
     80%|########  | 136M/170M [00:02<00:00, 56.4MB/s]
     83%|########3 | 142M/170M [00:02<00:00, 51.1MB/s]
     87%|########7 | 148M/170M [00:02<00:00, 54.5MB/s]
     90%|######### | 153M/170M [00:03<00:00, 42.6MB/s]
     94%|#########4| 160M/170M [00:03<00:00, 45.1MB/s]
     99%|#########8| 168M/170M [00:03<00:00, 53.5MB/s]
    100%|##########| 170M/170M [00:03<00:00, 51.6MB/s]
     /venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
       for i in range(dim)
     /venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -296,7 +296,7 @@ Get boxes with score larger than 0.9
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 3 minutes  21.658 seconds)
+   **Total running time of the script:** ( 3 minutes  16.971 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 7e72e1e3dd..a883aa64b2 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -236,7 +236,7 @@ training. Other models require a full post training calibration.
     /venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MobileNet_V2_Weights.IMAGENET1K_V1`. You can also use `weights=MobileNet_V2_Weights.DEFAULT` to get the most up-to-date weights.
       warnings.warn(msg)
     Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
      0%|          | 0.00/13.6M [00:00<?, ?B/s]
     59%|#####8    | 7.99M/13.6M [00:00<00:00, 59.0MB/s]
    100%|##########| 13.6M/13.6M [00:00<00:00, 61.4MB/s]
+
      0%|          | 0.00/13.6M [00:00<?, ?B/s]
     47%|####6     | 6.30M/13.6M [00:00<00:00, 63.1MB/s]
     91%|######### | 12.3M/13.6M [00:00<00:00, 44.4MB/s]
    100%|##########| 13.6M/13.6M [00:00<00:00, 50.0MB/s]
 
 
 
@@ -418,7 +418,7 @@ Here we give an example of how to measure performance of TVM compiled models.
 
     Execution time summary:
      mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)  
-      90.5403      90.5017      94.8389      90.1184       0.4960   
+      90.4050      90.3277      95.0359      90.0595       0.4947   
                
 
 
@@ -467,7 +467,7 @@ TODO
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  10.807 seconds)
+   **Total running time of the script:** ( 1 minutes  6.767 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 a2c09ec2d4..d40eb3fa1a 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
@@ -432,7 +432,7 @@ Here we give an example of how to measure performance of TVM compiled models.
 
     Execution time summary:
      mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)  
-      119.4717     119.3346     124.6189     118.5417      0.7517   
+      120.9329     120.8553     125.1488     120.2441      0.5669   
                
 
 
@@ -469,7 +469,7 @@ Here we give an example of how to measure performance of TVM compiled models.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 2 minutes  30.840 seconds)
+   **Total running time of the script:** ( 2 minutes  31.481 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 747dcfd459..42da9af580 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -253,7 +253,7 @@ We create a Relay VM to build and execute the model.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  42.918 seconds)
+   **Total running time of the script:** ( 1 minutes  39.807 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 df63205b13..0d73d00e9e 100644
--- a/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
@@ -166,7 +166,7 @@ Convert and compile model for CPU.
             data: None
       input_sym_arg_type = in_param.infer_type()[0]
     Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
      0%|          | 0/132723 [00:00<?, ?KB/s]
      5%|5         | 6912/132723 [00:00<00:01, 69106.06KB/s]
     11%|#1        | 15152/132723 [00:00<00:01, 68122.83KB/s]
     17%|#6        | 21972/132723 [00:00<00:02, 39543.87KB/s]
     23%|##2       | 30354/132723 [00:00<00:02, 51109.35KB/s]
     28%|##8       | 37497/132723 [00:00<00:01, 56165.70KB/s]
     34%|###3      | 44486/132723 [00:00<00:01, 59980.29KB/s]
     39%|###8      | 51150/132723 [00:00<00:01, 54000.24KB/s]
     45%|####4     | 59588/132723 [00:01<00:01, 61946.16KB/s]
     50%|####9     | 66313/132723 [00:01<00:01, 61297.42KB/s]
     56%|#####6    | 74717/132723 [00:01<00:00, 67508.51KB/s]
     62%|######1   | 81798/132723 [00:01<00:00, 62225.58KB/s]
     67%|######6   | 88311/132723 [00:01<00:01, 43222.78KB/s]
     73%|#######2  | 96688/132723 [00:01<00:00, 51636.36KB/s]
     78%|#######7  | 102894/132723 [00:01<00:00, 53736.48KB/s]
     84%|########3 | 111335/132723 [00:01<00:00, 61258.35KB/s]
     89%|########9
  | 118185/132723 [00:02<00:00, 50980.55KB/s]
     95%|#########5| 126549/132723 [00:02<00:00, 58502.28KB/s]
    100%|##########| 132723/132723 [00:02<00:00, 56851.09KB/s]
+
      0%|          | 0/132723 [00:00<?, ?KB/s]
      6%|5         | 7359/132723 [00:00<00:01, 73578.32KB/s]
     12%|#2        | 16072/132723 [00:00<00:01, 81546.45KB/s]
     18%|#8        | 24227/132723 [00:00<00:01, 62005.86KB/s]
     25%|##4       | 32757/132723 [00:00<00:02, 43299.33KB/s]
     31%|###1      | 41408/132723 [00:00<00:01, 53118.25KB/s]
     38%|###7      | 50040/132723 [00:00<00:01, 61252.25KB/s]
     44%|####4     | 58670/132723 [00:00<00:01, 67745.91KB/s]
     51%|#####     | 67351/132723 [00:01<00:00, 72896.78KB/s]
     57%|#####7    | 75784/132723 [00:01<00:00, 76080.18KB/s]
     63%|######3   | 84228/132723 [00:01<00:00, 78457.65KB/s]
     70%|######9   | 92783/132723 [00:01<00:00, 80506.54KB/s]
     76%|#######6  | 101108/132723 [00:01<00:00, 70659.05KB/s]
     83%|########2 | 109815/132723 [00:01<00:00, 75025.98KB/s]
     89%|########8 | 118048/132723 [00:01<00:00, 77036.58KB/s]
     95%|#########5| 126742/132723 [00:01<00:00, 79831.45KB/s]
    100%|#######
 ###| 132723/132723 [00:01<00:00, 69886.02KB/s]
 
 
 
@@ -242,7 +242,7 @@ Display result
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 3 minutes  3.754 seconds)
+   **Total running time of the script:** ( 3 minutes  2.439 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 5817719fc2..457a57626d 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,24 +5,24 @@
 
 Computation times
 =================
-**13:22.160** total execution time for **how_to_deploy_models** files:
+**13:04.439** total execution time for **how_to_deploy_models** files:
 
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:21.658 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:16.971 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)                           | 03:03.754 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)                           | 03:02.439 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)           | 02:30.840 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)           | 02:31.481 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)                               | 01:42.918 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)                               | 01:39.807 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)                         | 01:10.807 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)                         | 01:06.767 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)                 | 00:38.804 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)                 | 00:36.121 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``)                       | 00:26.989 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``)                       | 00:25.702 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)                       | 00:26.383 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)                       | 00:25.146 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``)                                     | 00:00.007 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
index 16ba889de5..4083b3b8a3 100644
--- a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
@@ -472,7 +472,7 @@ First let us define two helper functions to get the mobilenet model and a cat im
 
  .. code-block:: none
 
-    Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipccbf2386-7e57-408a-8b03-16a9002a6478 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+    Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipb5ec6e0e-1a2e-4ead-b5c9-a1715a34eb53 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 defc7dc9e1..170b276518 100644
--- a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
 
 Computation times
 =================
-**00:48.149** total execution time for **how_to_extend_tvm** files:
+**00:48.729** 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``) | 00:44.665 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:45.240 | 0.0 MB |
 +-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)           | 00:02.437 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)           | 00:02.441 | 0.0 MB |
 +-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)                     | 00:01.039 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)                     | 00:01.040 | 0.0 MB |
 +-------------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``)       | 00:00.008 | 0.0 MB |
 +-------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
index ee72902846..82afb7faa1 100644
--- a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
@@ -216,10 +216,10 @@ profile the execution time of each passes.
  .. code-block:: none
 
     Printing results of timing profile...
-    InferType: 7176us [7176us] (46.30%; 46.30%)
-    FoldScaleAxis: 8322us [6us] (53.70%; 53.70%)
-            FoldConstant: 8315us [1690us] (53.66%; 99.92%)
-                    InferType: 6626us [6626us] (42.75%; 79.68%)
+    InferType: 7091us [7091us] (45.25%; 45.25%)
+    FoldScaleAxis: 8579us [7us] (54.75%; 54.75%)
+            FoldConstant: 8572us [1775us] (54.70%; 99.92%)
+                    InferType: 6796us [6796us] (43.37%; 79.29%)
 
 
 
@@ -258,10 +258,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
  .. code-block:: none
 
     Printing results of timing profile...
-    InferType: 6651us [6651us] (45.01%; 45.01%)
-    FoldScaleAxis: 8127us [5us] (54.99%; 54.99%)
-            FoldConstant: 8122us [1678us] (54.96%; 99.94%)
-                    InferType: 6444us [6444us] (43.61%; 79.34%)
+    InferType: 6623us [6623us] (44.82%; 44.82%)
+    FoldScaleAxis: 8153us [5us] (55.18%; 55.18%)
+            FoldConstant: 8148us [1692us] (55.14%; 99.94%)
+                    InferType: 6456us [6456us] (43.69%; 79.24%)
 
 
 
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 7a42515b07..8edfefa1cd 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
@@ -340,7 +340,7 @@ latency of convolution.
 
  .. code-block:: none
 
-    Convolution: 41.190143 ms
+    Convolution: 34.213375 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 fea31eb590..d266275182 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
@@ -657,7 +657,7 @@ be able to run on our build server
 
  .. code-block:: none
 
-    conv2d with tensor core: 13.362189 ms
+    conv2d with tensor core: 13.353340 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 906070cc83..9271533431 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -143,8 +143,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
 
  .. code-block:: none
 
-    Numpy running time: 0.018437
-    Baseline: 3.542359
+    Numpy running time: 0.019583
+    Baseline: 3.429270
 
 
 
@@ -238,7 +238,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
 
  .. code-block:: none
 
-    Opt1: 0.305990
+    Opt1: 0.308873
 
 
 
@@ -340,7 +340,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
 
  .. code-block:: none
 
-    Opt2: 0.335689
+    Opt2: 0.331130
 
 
 
@@ -435,7 +435,7 @@ the access pattern for A matrix is more cache friendly.
 
  .. code-block:: none
 
-    Opt3: 0.116123
+    Opt3: 0.116499
 
 
 
@@ -559,7 +559,7 @@ flattening.
 
  .. code-block:: none
 
-    Opt4: 0.110101
+    Opt4: 0.109366
 
 
 
@@ -680,7 +680,7 @@ write to C when all the block results are ready.
 
  .. code-block:: none
 
-    Opt5: 0.111848
+    Opt5: 0.111082
 
 
 
@@ -804,7 +804,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
 
  .. code-block:: none
 
-    Opt6: 0.147245
+    Opt6: 0.147840
 
 
 
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 e86fca2eea..cf302c36db 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
 
 Computation times
 =================
-**00:35.417** total execution time for **how_to_optimize_operators** files:
+**00:35.433** total execution time for **how_to_optimize_operators** files:
 
 +-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)                       | 00:32.836 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)                       | 00:32.596 | 0.0 MB |
 +-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.521 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.698 | 0.0 MB |
 +-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)             | 00:01.061 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)             | 00:01.138 | 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 59f0199b5e..ba6acac68a 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
 =================
-**09:43.171** total execution time for **how_to_tune_with_autoscheduler** files:
+**09:22.962** 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``) | 06:07.710 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:52.239 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)             | 01:34.567 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)             | 01:34.879 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)           | 01:04.692 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)           | 01:04.373 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)               | 00:31.234 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)               | 00:27.840 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)             | 00:12.963 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)             | 00:12.218 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)           | 00:12.004 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)           | 00:11.414 | 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 a73cdc578d..8579666368 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
@@ -239,483 +239,191 @@ cooperative fetching, unrolling and operator fusion.
                  bias: Buffer(bias_2: Pointer(float32), float32, [1, 512, 1, 1], []),
                  compute: Buffer(compute_2: Pointer(float32), float32, [1, 512, 7, 7], [])}
       buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute} {
-      attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 28;
-      allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
-      allocate(pad_temp.shared: Pointer(shared float32), float32, [72]), storage_scope = shared;
-      allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
-      attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
-        conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
+      attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 128;
+      allocate(conv2d_nchw: Pointer(local float32), float32, [4]), storage_scope = local;
+      allocate(pad_temp.shared: Pointer(shared float32), float32, [324]), storage_scope = shared;
+      allocate(kernel.shared: Pointer(shared float32), float32, [144]), storage_scope = shared;
+      attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
+        conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=16)[0] = 0f32
         conv2d_nchw_1[1] = 0f32
         conv2d_nchw_1[2] = 0f32
         conv2d_nchw_1[3] = 0f32
-        conv2d_nchw_1[4] = 0f32
-        conv2d_nchw_1[5] = 0f32
-        conv2d_nchw_1[6] = 0f32
-        conv2d_nchw_1[7] = 0f32
-        conv2d_nchw_1[8] = 0f32
-        conv2d_nchw_1[9] = 0f32
-        conv2d_nchw_1[10] = 0f32
-        conv2d_nchw_1[11] = 0f32
-        conv2d_nchw_1[12] = 0f32
-        conv2d_nchw_1[13] = 0f32
-        for (rc.outer.outer: int32, 0, 64) {
-          for (ry.outer.outer: int32, 0, 3) {
-            let cse_var_2: int32 = (rc.outer.outer*72)
-            let cse_var_1: int32 = (ry.outer.outer*3)
-             {
-              attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
-                if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
-                  pad_temp.shared_1: Buffer(pad_temp.shared, float32, [72], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data_3: Buffer(data_2, float32, [25088], [])[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*4), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + fl [...]
-                }
-                if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
-                  pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data_3[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 1), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0f32, dtype=float32)
-                }
-                if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
-                  pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data_3[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 2), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0f32, dtype=float32)
-                }
-                if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
-                  pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data_3[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 3), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0f32, dtype=float32)
-                }
-              }
-              attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 64)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 64), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 128)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 128), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 192)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 256)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 256), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 320)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 320), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 384)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 448)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 448), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 512)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 512), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 576)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 640)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 640), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 704)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 704), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 768)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 147456)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 832)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 832), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 896)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 896), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 960)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 184320)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1024), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1088), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 221184)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1216), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1280), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1408), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1472), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 294912)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1600), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1664), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 331776)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1792), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1856), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 368640)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1984), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2048), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 405504)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2176), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2240), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 442368)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2368), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2432), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 479232)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2560), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2624), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 516096)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2752), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2816), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 552960)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2944), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3008), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*48)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*48)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*48)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*48)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*48)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*48)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*48)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+        for (rc.outer.outer: int32, 0, 128) {
+          let cse_var_2: int32 = (rc.outer.outer*196)
+          let cse_var_1: int32 = (rc.outer.outer*36)
+           {
+            attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+            pad_temp.shared_1: Buffer(pad_temp.shared, float32, [324], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((9 <= threadIdx.x_1) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data_3: Buffer(data_2, float32, [25088], [])[(((cse_var_2 + (floordiv(threadIdx.x_1, 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+            attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+            pad_temp.shared_1[(threadIdx.x_1 + 49)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 49), 81)) && (floormod((threadIdx.x_1 + 49), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 49), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 49), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+            attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+            pad_temp.shared_1[(threadIdx.x_1 + 98)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 8), 9)) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 98), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 17), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+            attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+            pad_temp.shared_1[(threadIdx.x_1 + 147)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 66), 81)) && (floormod((threadIdx.x_1 + 66), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 147), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 66), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+            attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+            pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 34), 81)) && (floormod((threadIdx.x_1 + 34), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 196), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 34), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+            attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+            pad_temp.shared_1[(threadIdx.x_1 + 245)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 2), 81)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 245), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 2), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+            attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+            if @tir.likely((threadIdx.x_1 < 30), dtype=bool) {
+              pad_temp.shared_1[(threadIdx.x_1 + 294)] = @tir.if_then_else((((threadIdx.x_1 < 21) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 294), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 51), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
             }
+            attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+            kernel.shared_1: Buffer(kernel.shared, float32, [144], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 36)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 36))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+            kernel.shared_1[(threadIdx.x_2 + 49)] = kernel_3[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 49), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 13), 36), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 4), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+            if @tir.likely((threadIdx.x_2 < 46), dtype=bool) {
+              kernel.shared_1[(threadIdx.x_2 + 98)] = kernel_3[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 98), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 26), 36), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 8), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+            }
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[0]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[9]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[36]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[45]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[72]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[81]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[108]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[117]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[1]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[10]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[37]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[46]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[73]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[82]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[109]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[118]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[2]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[11]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[38]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[47]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[74]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[83]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[110]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[119]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[3]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[12]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[39]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[48]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[75]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[84]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[111]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[120]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[4]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[13]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[40]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[49]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[76]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[85]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[112]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[121]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[5]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[14]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[41]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[50]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[77]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[86]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[113]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[122]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[6]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[15]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[42]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[51]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[78]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[87]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[114]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[123]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[7]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[16]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[43]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[52]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[79]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[88]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[115]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[124]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[8]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[17]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[44]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[53]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[80]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[89]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[116]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[125]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[18]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[27]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[54]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[63]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[90]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[99]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[126]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[135]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[19]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[28]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[55]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[64]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[91]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[100]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[127]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[136]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[20]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[29]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[56]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[65]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[92]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[101]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[128]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[137]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[21]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[30]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[57]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[66]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[93]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[102]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[129]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[138]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[22]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[31]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[58]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[67]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[94]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[103]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[130]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[139]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[23]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[32]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[59]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[68]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[95]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[104]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[131]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[140]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[24]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[33]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[60]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[69]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[96]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[105]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[132]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[141]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[25]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[34]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[61]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[70]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[97]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[106]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[133]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[142]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[26]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[35]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[62]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[71]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[98]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[107]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[134]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[143]))
           }
         }
-        for (i1.inner: int32, 0, 2) {
-          for (i3.inner: int32, 0, 7) {
-            compute_3: Buffer(compute_2, float32, [25088], [])[(((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias_3: Buffer(bias_2, float32, [512], [])[(((floordiv(blockIdx.x, 7)*128) + (threadIdx.x*2)) + i1.inner)]), 0f32)
-          }
+        for (i1.inner: int32, 0, 4) {
+          compute_3: Buffer(compute_2, float32, [25088], [])[(((blockIdx.x*196) + (i1.inner*49)) + threadIdx.x)] = max((conv2d_nchw_1[i1.inner] + bias_3: Buffer(bias_2, float32, [512], [])[((blockIdx.x*4) + i1.inner)]), 0f32)
         }
       }
     }
@@ -770,7 +478,7 @@ We build the binary and check its correctness and performance.
 
  .. code-block:: none
 
-    Execution time of this operator: 0.349 ms
+    Execution time of this operator: 0.259 ms
 
 
 
@@ -819,35 +527,35 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
     conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
     conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
     conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
-    conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
-    conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
+    conv2d_nchw_ff_o_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=1)
     conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
     conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
     conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
-    conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
+    conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
     conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
     conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
-    conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
-    conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
+    conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
+    conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
     conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
     conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
-    conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
+    conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
     conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
-    conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
+    conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
     conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
     conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
     s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
     compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
     compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
     compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
-    compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
-    compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
+    compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=4)
+    compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=1)
     compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
     compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
-    compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+    compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
     compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
-    compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
-    compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
+    compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
+    compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
     compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
     s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
     s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -867,12 +575,12 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
     kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
     kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
     s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-    kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
+    kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=49)
     s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
     pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
-    pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=4)
+    pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
     s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-    pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
+    pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=49)
     s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
     s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
     s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
@@ -892,430 +600,178 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
       #define int64_t long long
       #define uint64_t unsigned long long
     #endif
-    extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
-      float conv2d_nchw[14];
-      __shared__ float pad_temp_shared[72];
-      __shared__ float kernel_shared[3072];
+    extern "C" __global__ void __launch_bounds__(49) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+      float conv2d_nchw[4];
+      __shared__ float pad_temp_shared[324];
+      __shared__ float kernel_shared[144];
       conv2d_nchw[0] = 0.000000e+00f;
       conv2d_nchw[1] = 0.000000e+00f;
       conv2d_nchw[2] = 0.000000e+00f;
       conv2d_nchw[3] = 0.000000e+00f;
-      conv2d_nchw[4] = 0.000000e+00f;
-      conv2d_nchw[5] = 0.000000e+00f;
-      conv2d_nchw[6] = 0.000000e+00f;
-      conv2d_nchw[7] = 0.000000e+00f;
-      conv2d_nchw[8] = 0.000000e+00f;
-      conv2d_nchw[9] = 0.000000e+00f;
-      conv2d_nchw[10] = 0.000000e+00f;
-      conv2d_nchw[11] = 0.000000e+00f;
-      conv2d_nchw[12] = 0.000000e+00f;
-      conv2d_nchw[13] = 0.000000e+00f;
-      for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
-        for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
-          __syncthreads();
-          if (((int)threadIdx.x) < 18) {
-            pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
-          }
-          if (((int)threadIdx.x) < 18) {
-            pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
-          }
-          if (((int)threadIdx.x) < 18) {
-            pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
-          }
-          if (((int)threadIdx.x) < 18) {
-            pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
-          }
-          kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
-          kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
-          kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
-          kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
-          kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
-          kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
-          kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
-          kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
-          kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
-          kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
-          kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
-          kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
-          kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
-          kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
-          kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
-          kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          __syncthreads();
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 48)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 48)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 48)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 48)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 48)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 48)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 48)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+      for (int rc_outer_outer = 0; rc_outer_outer < 128; ++rc_outer_outer) {
+        __syncthreads();
+        pad_temp_shared[((int)threadIdx.x)] = ((((9 <= ((int)threadIdx.x)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+        pad_temp_shared[(((int)threadIdx.x) + 49)] = (((((9 <= ((((int)threadIdx.x) + 49) % 81)) && (((((int)threadIdx.x) + 49) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 49) / 81) * 49)) + ((((((int)threadIdx.x) + 49) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 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) / 81) * 49)) + (((((int)threadIdx.x) + 17) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+        pad_temp_shared[(((int)threadIdx.x) + 147)] = (((((9 <= ((((int)threadIdx.x) + 66) % 81)) && (((((int)threadIdx.x) + 66) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 147) / 81) * 49)) + ((((((int)threadIdx.x) + 66) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+        pad_temp_shared[(((int)threadIdx.x) + 196)] = (((((9 <= ((((int)threadIdx.x) + 34) % 81)) && (((((int)threadIdx.x) + 34) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 196) / 81) * 49)) + ((((((int)threadIdx.x) + 34) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+        pad_temp_shared[(((int)threadIdx.x) + 245)] = ((((7 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 245) / 81) * 49)) + (((((int)threadIdx.x) + 2) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+        if (((int)threadIdx.x) < 30) {
+          pad_temp_shared[(((int)threadIdx.x) + 294)] = ((((((int)threadIdx.x) < 21) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 294) / 81) * 49)) + (((((int)threadIdx.x) + 51) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
         }
-      }
-      for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
-        for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
-          compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
+        kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) % 36))];
+        kernel_shared[(((int)threadIdx.x) + 49)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 49) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 13) % 36) / 9) * 9)) + ((((((int)threadIdx.x) + 4) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+        if (((int)threadIdx.x) < 46) {
+          kernel_shared[(((int)threadIdx.x) + 98)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 98) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 26) % 36) / 9) * 9)) + ((((((int)threadIdx.x) + 8) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
         }
+        __syncthreads();
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[0]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[9]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[36]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[45]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[72]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[81]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[108]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[117]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[1]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[10]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[37]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[46]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[73]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[82]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[109]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[118]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[2]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[11]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[38]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[47]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[74]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[83]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[110]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[119]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[3]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[12]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[39]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[48]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[75]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[84]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[111]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[120]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[4]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[13]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[40]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[49]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[76]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[85]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[112]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[121]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[5]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[14]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[41]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[50]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[77]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[86]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[113]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[122]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[6]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[15]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[42]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[51]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[78]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[87]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[114]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[123]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[7]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[16]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[43]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[52]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[79]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[88]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[115]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[124]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[8]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[17]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[44]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[53]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[80]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[89]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[116]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[125]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[18]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[27]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[54]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[63]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[90]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[99]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[126]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[135]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[19]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[28]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[55]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[64]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[91]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[100]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[127]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[136]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[20]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[29]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[56]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[65]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[92]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[101]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[128]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[137]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[21]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[30]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[57]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[66]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[93]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[102]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[129]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[138]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[22]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[31]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[58]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[67]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[94]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[103]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[130]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[139]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[23]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[32]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[59]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[68]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[95]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[104]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[131]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[140]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[24]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[33]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[60]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[69]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[96]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[105]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[132]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[141]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[25]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[34]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[61]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[70]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[97]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[106]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[133]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[142]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[26]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[35]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[62]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[71]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[98]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[107]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[134]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[143]));
+      }
+      for (int i1_inner = 0; i1_inner < 4; ++i1_inner) {
+        compute[(((((int)blockIdx.x) * 196) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 4) + i1_inner)]), 0.000000e+00f);
       }
     }
 
@@ -1369,7 +825,7 @@ In the example below we resume the status and do more 5 trials.
     /venv/apache-tvm-py3.7/lib/python3.7/site-packages/xgboost/training.py:17: UserWarning: Old style callback is deprecated.  See: https://xgboost.readthedocs.io/en/latest/python/callbacks.html
       warnings.warn(f'Old style callback is deprecated.  See: {link}', UserWarning)
     Get devices for measurement successfully!
-
+    .T
 
 
 
@@ -1377,7 +833,7 @@ In the example below we resume the status and do more 5 trials.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 6 minutes  7.710 seconds)
+   **Total running time of the script:** ( 5 minutes  52.239 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 ef7db935ab..175fd78ad6 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -643,7 +643,7 @@ so we can read the log file and load the best schedules.
     Evaluate inference time cost...
     Execution time summary:
      mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)  
-       8.1987       8.1995       8.2098       8.1868       0.0094   
+       8.2691       8.2682       8.2786       8.2605       0.0074   
                
 
 
@@ -671,7 +671,7 @@ Other Tips
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  4.692 seconds)
+   **Total running time of the script:** ( 1 minutes  4.373 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 638bd36263..ca33a85f14 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
@@ -662,7 +662,7 @@ so we can read the log file and load the best schedules.
     Evaluate inference time cost...
     Execution time summary:
      mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)  
-      752.0948     752.5188     753.8207     749.9449      1.6104   
+      765.1622     765.7585     766.9518     762.7763      1.7560   
                
 
 
@@ -690,7 +690,7 @@ Other Tips
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  34.567 seconds)
+   **Total running time of the script:** ( 1 minutes  34.879 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 3b4c7fa08c..55f0ff3cad 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
@@ -386,28 +386,31 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
                  placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [128, 512], []),
                  compute: Buffer(compute_2: Pointer(float32), float32, [128, 512], [])}
       buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute} {
-      for (i0.outer.i1.outer.fused: int32, 0, 32) "parallel" {
-        allocate(compute_3: Pointer(global float32), float32, [2048]), storage_scope = global {
-          for (i.outer.inner: int32, 0, 2) {
-            for (i.inner.init: int32, 0, 64) {
+      for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
+        allocate(compute_3: Pointer(global float32), float32, [512]), storage_scope = global {
+          for (i.outer.inner: int32, 0, 8) {
+            for (i.inner.init: int32, 0, 4) {
               for (j.init: int32, 0, 16) {
-                compute_4: Buffer(compute_3, float32, [2048], [])[(((i.outer.inner*1024) + (i.inner.init*16)) + j.init)] = 0f32
+                compute_4: Buffer(compute_3, float32, [512], [])[(((i.outer.inner*64) + (i.inner.init*16)) + j.init)] = 0f32
               }
             }
-            for (elem_idx: int32, 0, (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])) {
-              for (i.inner: int32, 0, 64) {
+            for (elem_idx: int32, 0, let cse_var_1: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_1 + 1)] - placeholder_15[cse_var_1])) {
+              for (i.inner: int32, 0, 4) {
                 for (j: int32, 0, 16) {
-                  if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
-                    let cse_var_1: int32 = (((i.outer.inner*1024) + (i.inner*16)) + j)
-                    compute_4[cse_var_1] = (compute_4[cse_var_1] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + j)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+                  let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32)
+                  if @tir.likely((elem_idx < (placeholder_15[(cse_var_2 + 1)] - placeholder_15[cse_var_2])), dtype=bool) {
+                    let cse_var_3: int32 = (((i.outer.inner*64) + (i.inner*16)) + j)
+                    compute_4[cse_var_3] = (compute_4[cse_var_3] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[(((placeholder_15[cse_var_2]*16) + (elem_idx*16)) + j)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_2] + elem_idx)])], 0f32)))
                   }
                 }
               }
             }
           }
-          for (i0.inner: int32, 0, 128) {
-            let cse_var_2: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*16))
-            compute_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_2, 1, 16)] = max((compute_4[ramp((i0.inner*16), 1, 16)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_2, 1, 16)]), broadcast(0f32, 16))
+          for (i0.inner: int32, 0, 32) {
+            for (i1.inner: int32, 0, 16) {
+              let cse_var_4: int32 = ((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16)) + i1.inner)
+              compute_5: Buffer(compute_2, float32, [65536], [])[cse_var_4] = max((compute_4[((i0.inner*16) + i1.inner)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[cse_var_4]), 0f32)
+            }
           }
         }
       }
@@ -463,7 +466,7 @@ We build the binary and check its correctness and performance.
 
  .. code-block:: none
 
-    Execution time of this operator: 1.807 ms
+    Execution time of this operator: 1.477 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 220922d074..57c9bc35a2 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
 
 Computation times
 =================
-**00:33.070** total execution time for **how_to_tune_with_autotvm** files:
+**00:31.477** 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``)           | 00:33.035 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)           | 00:31.441 | 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 |
 +--------------------------------------------------------------------------------------------------+-----------+--------+
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 71d5a1af55..f4ce89995b 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
@@ -265,9 +265,7 @@ for this template
     waiting for device...
     device available
     Get devices for measurement successfully!
-    No: 1   GFLOPS: 62.40/62.40     result: MeasureResult(costs=(0.003710196272727273,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.506129264831543, timestamp=1668612674.5134175)        [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 7, 1]), ('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', 1500), ('unroll_explicit', 0)],None,4520238
-    No: 2   GFLOPS: 46.81/62.40     result: MeasureResult(costs=(0.004945171857142857,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.2848103046417236, timestamp=1668612676.0735888)       [('tile_f', [-1, 4, 16, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4185807
-    No: 3   GFLOPS: 0.00/62.40      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 588, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -389,8 +387,8 @@ 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 871, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 64, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4948265
-    No: 4   GFLOPS: 0.00/62.40      result: Traceback (most recent call last):
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 2, 32, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3647031
+    No: 2   GFLOPS: 0.00/0.00       result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -512,9 +510,9 @@ 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 871, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 1, 32, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3192384
-    No: 5   GFLOPS: 4.12/62.40      result: MeasureResult(costs=(0.05621964625,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.726212501525879, timestamp=1668612679.9325876)       [('tile_f', [-1, 8, 4, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,74952
-    No: 6   GFLOPS: 0.00/62.40      result: Traceback (most recent call last):
+    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, 2, 256]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5803149
+    No: 3   GFLOPS: 228.85/228.85   result: MeasureResult(costs=(0.0010115684646464648,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.749254941940308, timestamp=1668618422.8077989)       [('tile_f', [-1, 4, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7984692
+    No: 4   GFLOPS: 0.00/228.85     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -636,10 +634,8 @@ 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 871, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 16, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5528183
-    No: 7   GFLOPS: 200.02/200.02   result: MeasureResult(costs=(0.001157369597122302,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7944960594177246, timestamp=1668612681.7724178)       [('tile_f', [-1, 1, 16, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8467394
-    No: 8   GFLOPS: 87.19/200.02    result: MeasureResult(costs=(0.0026551532195121953,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1284987926483154, timestamp=1668612682.474605)       [('tile_f', [-1, 1, 2, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,127224
-    No: 9   GFLOPS: 0.00/200.02     result: Traceback (most recent call last):
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 1, 128, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,350595
+    No: 5   GFLOPS: 0.00/228.85     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -761,10 +757,9 @@ 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 871, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 1, 32, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7907720
-    No: 10  GFLOPS: 46.96/200.02    result: MeasureResult(costs=(0.004929517181818182,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.243342876434326, timestamp=1668612685.9050357)        [('tile_f', [-1, 1, 2, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3789950
-    No: 11  GFLOPS: 413.73/413.73   result: MeasureResult(costs=(0.0005595513016759776,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5997123718261719, timestamp=1668612686.585363)       [('tile_f', [-1, 8, 4, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7978322
-    No: 12  GFLOPS: 0.00/413.73     result: Traceback (most recent call last):
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 1, 16, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9650018
+    No: 6   GFLOPS: 126.37/228.85   result: MeasureResult(costs=(0.001831866727272727,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.34965181350708, timestamp=1668618425.2790372) [('tile_f', [-1, 1, 4, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2177455
+    No: 7   GFLOPS: 0.00/228.85     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -886,8 +881,8 @@ 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 871, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 8, 16, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2832097
-    No: 13  GFLOPS: 0.00/413.73     result: Traceback (most recent call last):
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 16, 4, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7101279
+    No: 8   GFLOPS: 0.00/228.85     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1009,8 +1004,8 @@ 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 871, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 32, 4, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7831240
-    No: 14  GFLOPS: 0.00/413.73     result: Traceback (most recent call last):
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 2, 128, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5089138
+    No: 9   GFLOPS: 0.00/228.85     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1132,8 +1127,8 @@ 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 871, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4861104
-    No: 15  GFLOPS: 0.00/413.73     result: Traceback (most recent call last):
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 32, 4, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,943480
+    No: 10  GFLOPS: 0.00/228.85     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1255,8 +1250,8 @@ 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 871, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 16, 8, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7030351
-    No: 16  GFLOPS: 0.00/413.73     result: Traceback (most recent call last):
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 4, 64, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7111376
+    No: 11  GFLOPS: 0.00/228.85     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1378,8 +1373,8 @@ 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 871, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 64, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2939086
-    No: 17  GFLOPS: 0.00/413.73     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, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8769711
+    No: 12  GFLOPS: 0.00/228.85     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1501,8 +1496,8 @@ 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 871, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 1, 1, 256]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10112296
-    No: 18  GFLOPS: 0.00/413.73     result: Traceback (most recent call last):
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 1, 128, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8437575
+    No: 13  GFLOPS: 0.00/228.85     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1624,9 +1619,8 @@ 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 871, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 32, 8, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4543744
-    No: 19  GFLOPS: 439.07/439.07   result: MeasureResult(costs=(0.000527258671875,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0887837409973145, timestamp=1668612689.1139297)  [('tile_f', [-1, 1, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9168643
-    No: 20  GFLOPS: 0.00/439.07     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, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6925666
+    No: 14  GFLOPS: 0.00/228.85     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1748,7 +1742,379 @@ 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 871, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
-    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 2, 128, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10412870
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 1, 1, 512]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2489299
+    No: 15  GFLOPS: 0.00/228.85     result: Traceback (most recent call last):
+      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
+        func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
+        func = build(s, args, target_host=task.target_host, runtime=runtime)
+      File "/workspace/python/tvm/driver/build_module.py", line 227, in build
+        input_mod = lower(inputs, args, name=name, binds=binds)
+      File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
+        return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+      File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+      File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+      File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
+    tvm._ffi.base.TVMError: Traceback (most recent call last):
+      24: TVMFuncCall
+            at ../src/runtime/c_runtime_api.cc:477
+      23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+            at ../include/tvm/runtime/packed_func.h:1217
+      22: Call
+            at ../include/tvm/runtime/packed_func.h:1213
+      21: operator()
+            at ../include/tvm/runtime/packed_func.h:1731
+      20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+            at ../include/tvm/runtime/packed_func.h:1671
+      19: run<>
+            at ../include/tvm/runtime/packed_func.h:1631
+      18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1631
+      17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1631
+      16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1631
+      15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1631
+      14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1646
+      13: operator()
+            at ../src/driver/driver_api.cc:388
+      12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+            at ../src/driver/driver_api.cc:374
+      11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+            at ../src/driver/driver_api.cc:269
+      10: tvm::transform::Pass::operator()(tvm::IRModule) const
+            at ../src/ir/transform.cc:258
+      9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/ir/transform.cc:274
+      8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/ir/transform.cc:453
+      7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/ir/transform.cc:274
+      6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/tir/ir/transform.cc:100
+      5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+            at ../include/tvm/runtime/packed_func.h:1750
+      4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+            at ../include/tvm/runtime/packed_func.h:1694
+      3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+            at ../include/tvm/runtime/packed_func.h:1618
+      2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+            at ../include/tvm/runtime/packed_func.h:1217
+      1: Call
+            at ../include/tvm/runtime/packed_func.h:1213
+      0: operator()
+            at ../src/runtime/c_runtime_api.cc:534
+      File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
+        raise InstantiationError("Skipped because of invalid gpu kernel")
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
+
+    Traceback (most recent call last):
+      24: TVMFuncCall
+            at ../src/runtime/c_runtime_api.cc:477
+      23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+            at ../include/tvm/runtime/packed_func.h:1217
+      22: Call
+            at ../include/tvm/runtime/packed_func.h:1213
+      21: operator()
+            at ../include/tvm/runtime/packed_func.h:1731
+      20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+            at ../include/tvm/runtime/packed_func.h:1671
+      19: run<>
+            at ../include/tvm/runtime/packed_func.h:1631
+      18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1631
+      17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1631
+      16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1631
+      15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1631
+      14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1646
+      13: operator()
+            at ../src/driver/driver_api.cc:388
+      12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+            at ../src/driver/driver_api.cc:374
+      11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+            at ../src/driver/driver_api.cc:269
+      10: tvm::transform::Pass::operator()(tvm::IRModule) const
+            at ../src/ir/transform.cc:258
+      9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/ir/transform.cc:274
+      8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/ir/transform.cc:453
+      7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/ir/transform.cc:274
+      6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/tir/ir/transform.cc:100
+      5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+            at ../include/tvm/runtime/packed_func.h:1750
+      4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+            at ../include/tvm/runtime/packed_func.h:1694
+      3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+            at ../include/tvm/runtime/packed_func.h:1618
+      2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+            at ../include/tvm/runtime/packed_func.h:1217
+      1: Call
+            at ../include/tvm/runtime/packed_func.h:1213
+      0: operator()
+            at ../src/runtime/c_runtime_api.cc:534
+      File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
+        raise InstantiationError("Skipped because of invalid gpu kernel")
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 256, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2867938
+    No: 16  GFLOPS: 0.00/228.85     result: Traceback (most recent call last):
+      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
+        func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
+        func = build(s, args, target_host=task.target_host, runtime=runtime)
+      File "/workspace/python/tvm/driver/build_module.py", line 227, in build
+        input_mod = lower(inputs, args, name=name, binds=binds)
+      File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
+        return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+      File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+      File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+      File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
+    tvm._ffi.base.TVMError: Traceback (most recent call last):
+      24: TVMFuncCall
+            at ../src/runtime/c_runtime_api.cc:477
+      23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+            at ../include/tvm/runtime/packed_func.h:1217
+      22: Call
+            at ../include/tvm/runtime/packed_func.h:1213
+      21: operator()
+            at ../include/tvm/runtime/packed_func.h:1731
+      20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+            at ../include/tvm/runtime/packed_func.h:1671
+      19: run<>
+            at ../include/tvm/runtime/packed_func.h:1631
+      18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1631
+      17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1631
+      16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1631
+      15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1631
+      14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1646
+      13: operator()
+            at ../src/driver/driver_api.cc:388
+      12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+            at ../src/driver/driver_api.cc:374
+      11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+            at ../src/driver/driver_api.cc:269
+      10: tvm::transform::Pass::operator()(tvm::IRModule) const
+            at ../src/ir/transform.cc:258
+      9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/ir/transform.cc:274
+      8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/ir/transform.cc:453
+      7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/ir/transform.cc:274
+      6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/tir/ir/transform.cc:100
+      5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+            at ../include/tvm/runtime/packed_func.h:1750
+      4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+            at ../include/tvm/runtime/packed_func.h:1694
+      3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+            at ../include/tvm/runtime/packed_func.h:1618
+      2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+            at ../include/tvm/runtime/packed_func.h:1217
+      1: Call
+            at ../include/tvm/runtime/packed_func.h:1213
+      0: operator()
+            at ../src/runtime/c_runtime_api.cc:534
+      File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
+        raise InstantiationError("Skipped because of invalid gpu kernel")
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
+
+    Traceback (most recent call last):
+      24: TVMFuncCall
+            at ../src/runtime/c_runtime_api.cc:477
+      23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+            at ../include/tvm/runtime/packed_func.h:1217
+      22: Call
+            at ../include/tvm/runtime/packed_func.h:1213
+      21: operator()
+            at ../include/tvm/runtime/packed_func.h:1731
+      20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+            at ../include/tvm/runtime/packed_func.h:1671
+      19: run<>
+            at ../include/tvm/runtime/packed_func.h:1631
+      18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1631
+      17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1631
+      16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1631
+      15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1631
+      14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1646
+      13: operator()
+            at ../src/driver/driver_api.cc:388
+      12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+            at ../src/driver/driver_api.cc:374
+      11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+            at ../src/driver/driver_api.cc:269
+      10: tvm::transform::Pass::operator()(tvm::IRModule) const
+            at ../src/ir/transform.cc:258
+      9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/ir/transform.cc:274
+      8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/ir/transform.cc:453
+      7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/ir/transform.cc:274
+      6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/tir/ir/transform.cc:100
+      5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+            at ../include/tvm/runtime/packed_func.h:1750
+      4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+            at ../include/tvm/runtime/packed_func.h:1694
+      3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+            at ../include/tvm/runtime/packed_func.h:1618
+      2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+            at ../include/tvm/runtime/packed_func.h:1217
+      1: Call
+            at ../include/tvm/runtime/packed_func.h:1213
+      0: operator()
+            at ../src/runtime/c_runtime_api.cc:534
+      File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
+        raise InstantiationError("Skipped because of invalid gpu kernel")
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 1, 256, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9065199
+    No: 17  GFLOPS: 53.80/228.85    result: MeasureResult(costs=(0.00430309384,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4398438930511475, timestamp=1668618429.2793698)      [('tile_f', [-1, 1, 64, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6780343
+    No: 18  GFLOPS: 0.00/228.85     result: Traceback (most recent call last):
+      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
+        func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
+        func = build(s, args, target_host=task.target_host, runtime=runtime)
+      File "/workspace/python/tvm/driver/build_module.py", line 227, in build
+        input_mod = lower(inputs, args, name=name, binds=binds)
+      File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
+        return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+      File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+      File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+      File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
+    tvm._ffi.base.TVMError: Traceback (most recent call last):
+      24: TVMFuncCall
+            at ../src/runtime/c_runtime_api.cc:477
+      23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+            at ../include/tvm/runtime/packed_func.h:1217
+      22: Call
+            at ../include/tvm/runtime/packed_func.h:1213
+      21: operator()
+            at ../include/tvm/runtime/packed_func.h:1731
+      20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+            at ../include/tvm/runtime/packed_func.h:1671
+      19: run<>
+            at ../include/tvm/runtime/packed_func.h:1631
+      18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1631
+      17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1631
+      16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1631
+      15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1631
+      14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1646
+      13: operator()
+            at ../src/driver/driver_api.cc:388
+      12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+            at ../src/driver/driver_api.cc:374
+      11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+            at ../src/driver/driver_api.cc:269
+      10: tvm::transform::Pass::operator()(tvm::IRModule) const
+            at ../src/ir/transform.cc:258
+      9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/ir/transform.cc:274
+      8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/ir/transform.cc:453
+      7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/ir/transform.cc:274
+      6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/tir/ir/transform.cc:100
+      5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+            at ../include/tvm/runtime/packed_func.h:1750
+      4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+            at ../include/tvm/runtime/packed_func.h:1694
+      3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+            at ../include/tvm/runtime/packed_func.h:1618
+      2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+            at ../include/tvm/runtime/packed_func.h:1217
+      1: Call
+            at ../include/tvm/runtime/packed_func.h:1213
+      0: operator()
+            at ../src/runtime/c_runtime_api.cc:534
+      File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
+        raise InstantiationError("Skipped because of invalid gpu kernel")
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
+
+    Traceback (most recent call last):
+      24: TVMFuncCall
+            at ../src/runtime/c_runtime_api.cc:477
+      23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+            at ../include/tvm/runtime/packed_func.h:1217
+      22: Call
+            at ../include/tvm/runtime/packed_func.h:1213
+      21: operator()
+            at ../include/tvm/runtime/packed_func.h:1731
+      20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+            at ../include/tvm/runtime/packed_func.h:1671
+      19: run<>
+            at ../include/tvm/runtime/packed_func.h:1631
+      18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1631
+      17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1631
+      16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1631
+      15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1631
+      14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+            at ../include/tvm/runtime/packed_func.h:1646
+      13: operator()
+            at ../src/driver/driver_api.cc:388
+      12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+            at ../src/driver/driver_api.cc:374
+      11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+            at ../src/driver/driver_api.cc:269
+      10: tvm::transform::Pass::operator()(tvm::IRModule) const
+            at ../src/ir/transform.cc:258
+      9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/ir/transform.cc:274
+      8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/ir/transform.cc:453
+      7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/ir/transform.cc:274
+      6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+            at ../src/tir/ir/transform.cc:100
+      5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+            at ../include/tvm/runtime/packed_func.h:1750
+      4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+            at ../include/tvm/runtime/packed_func.h:1694
+      3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+            at ../include/tvm/runtime/packed_func.h:1618
+      2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+            at ../include/tvm/runtime/packed_func.h:1217
+      1: Call
+            at ../include/tvm/runtime/packed_func.h:1213
+      0: operator()
+            at ../src/runtime/c_runtime_api.cc:534
+      File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+      File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
+        raise InstantiationError("Skipped because of invalid gpu kernel")
+    tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 4, 4, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,639717
+    No: 19  GFLOPS: 37.57/228.85    result: MeasureResult(costs=(0.006161984117647059,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3533060550689697, timestamp=1668618430.00153) [('tile_f', [-1, 32, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5658415
+    No: 20  GFLOPS: 2.70/228.85     result: MeasureResult(costs=(0.085883934,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.988248109817505, timestamp=1668618431.4606593) [('tile_f', [-1, 32, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2554875
 
 
 
@@ -1803,9 +2169,9 @@ and measure running time.
     Finish loading 20 records
 
     Best config:
-    [('tile_f', [-1, 1, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9168643
+    [('tile_f', [-1, 4, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7984692
     Finish loading 20 records
-    Time cost of this operator: 0.000886
+    Time cost of this operator: 0.000809
 
 
 
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 70d4e25b46..924b1c7bc1 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
@@ -327,10 +327,10 @@ Timing the untuned program
     ########## Build without Autotuning ##########
     Node Name                                     Ops                                           Time(us)  Time(%)  Shape              Inputs  Outputs  Measurements(us)  
     ---------                                     ---                                           --------  -------  -----              ------  -------  ----------------  
-    tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  311.8     98.714   (1, 2, 10, 10, 3)  2       1        [311.8]           
-    tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       3.102     0.982    (1, 6, 10, 10)     1       1        [3.102]           
-    tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.962     0.305    (1, 1, 10, 10, 3)  1       1        [0.962]           
-    Total_time                                    -                                             315.863   -        -                  -       -        -                 
+    tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  313.9     98.712   (1, 2, 10, 10, 3)  2       1        [313.9]           
+    tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       3.131     0.985    (1, 6, 10, 10)     1       1        [3.131]           
+    tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.964     0.303    (1, 1, 10, 10, 3)  1       1        [0.964]           
+    Total_time                                    -                                             317.996   -        -                  -       -        -                 
 
 
 
@@ -394,10 +394,10 @@ 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  106.6     97.612   (1, 6, 10, 10, 1)  2       1        [106.6]           
-    tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       1.77      1.621    (1, 6, 10, 10)     1       1        [1.77]            
-    tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.838     0.767    (1, 3, 10, 10, 1)  1       1        [0.838]           
-    Total_time                                    -                                             109.208   -        -                  -       -        -                 
+    tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  102.6     97.476   (1, 6, 10, 10, 1)  2       1        [102.6]           
+    tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       1.799     1.709    (1, 6, 10, 10)     1       1        [1.799]           
+    tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.858     0.815    (1, 3, 10, 10, 1)  1       1        [0.858]           
+    Total_time                                    -                                             105.257   -        -                  -       -        -                 
 
 
 
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 8d471f7855..814f6e0438 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
@@ -109,7 +109,7 @@ download a cat image and preprocess it to use as the model input.
     /venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/ao/quantization/utils.py:281: UserWarning: must run observer before calling calculate_qparams. Returning default values.
       "must run observer before calling calculate_qparams. " +
     Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
-
      0%|          | 0.00/3.42M [00:00<?, ?B/s]
    100%|##########| 3.42M/3.42M [00:00<00:00, 81.3MB/s]
+
      0%|          | 0.00/3.42M [00:00<?, ?B/s]
    100%|##########| 3.42M/3.42M [00:00<00:00, 75.6MB/s]
     /workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
       return LooseVersion(torch_ver) > ver
     /venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -314,7 +314,7 @@ Look up prediction top 1 index in 1000 class synset.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  6.472 seconds)
+   **Total running time of the script:** ( 1 minutes  4.241 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 230bcc304f..d4ec269a98 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
@@ -225,7 +225,7 @@ take about **2 minutes** to download the Stanford Cars, while COCO 2017 validati
  .. code-block:: none
 
 
-    '/tmp/tmpy5o6f33_/images/random'
+    '/tmp/tmpbz6hkicy/images/random'
 
 
 
@@ -316,7 +316,7 @@ objects to other stuff? We can display some examples from our datasets using ``m
 
 
 .. image-sg:: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
-   :alt: [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [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], [1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]
    :srcset: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
    :class: sphx-glr-single-img
 
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
 
  .. code-block:: none
 
-    /tmp/tmpy5o6f33_/images/target contains 8144 images
-    /tmp/tmpy5o6f33_/images/random contains 5000 images
+    /tmp/tmpbz6hkicy/images/target contains 8144 images
+    /tmp/tmpbz6hkicy/images/random contains 5000 images
 
 
 
@@ -501,13 +501,13 @@ the time on our validation set).
  .. code-block:: none
 
     Epoch 1/3
-    328/328 - 47s - loss: 0.2249 - accuracy: 0.9236 - val_loss: 0.1049 - val_accuracy: 0.9603 - 47s/epoch - 144ms/step
+    328/328 - 47s - loss: 0.2374 - accuracy: 0.9209 - val_loss: 0.1806 - val_accuracy: 0.9388 - 47s/epoch - 143ms/step
     Epoch 2/3
-    328/328 - 43s - loss: 0.1043 - accuracy: 0.9625 - val_loss: 0.1249 - val_accuracy: 0.9596 - 43s/epoch - 133ms/step
+    328/328 - 44s - loss: 0.1106 - accuracy: 0.9570 - val_loss: 0.0969 - val_accuracy: 0.9641 - 44s/epoch - 133ms/step
     Epoch 3/3
-    328/328 - 43s - loss: 0.0645 - accuracy: 0.9761 - val_loss: 0.1150 - val_accuracy: 0.9656 - 43s/epoch - 132ms/step
+    328/328 - 43s - loss: 0.0756 - accuracy: 0.9724 - val_loss: 0.0981 - val_accuracy: 0.9690 - 43s/epoch - 132ms/step
 
-    <keras.callbacks.History object at 0x7f09494f4550>
+    <keras.callbacks.History object at 0x7f5cc00bee90>
 
 
 
@@ -864,7 +864,7 @@ Arduino tutorial for how to do that `on GitHub <https://github.com/guberti/tvm-a
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 4 minutes  38.542 seconds)
+   **Total running time of the script:** ( 4 minutes  47.987 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 588e43a29f..80c36ae27e 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,16 +5,16 @@
 
 Computation times
 =================
-**06:48.119** total execution time for **how_to_work_with_microtvm** files:
+**06:54.261** total execution time for **how_to_work_with_microtvm** files:
 
 +---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``)               | 04:38.542 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``)               | 04:47.987 | 0.0 MB |
 +---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``)           | 01:06.472 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``)           | 01:04.241 | 0.0 MB |
 +---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)         | 00:50.409 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)         | 00:49.982 | 0.0 MB |
 +---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``)                   | 00:08.910 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``)                   | 00:08.264 | 0.0 MB |
 +---------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)             | 00:03.784 | 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 2ed63129e6..f7a06f5e88 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
 =================
-**00:44.620** total execution time for **how_to_work_with_relay** files:
+**00:43.314** 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``) | 00:32.524 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:31.790 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)           | 00:10.560 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)           | 00:10.146 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)                             | 00:01.529 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)                             | 00:01.372 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``)                 | 00:00.007 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
index 888f99bc9b..4a1db0750a 100644
--- a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
@@ -261,7 +261,7 @@ The following example customizes CUDA lowering rule for :code:`exp`.
  .. code-block:: none
 
 
-    <function my_cuda_math_rule at 0x7f0949fdbdd0>
+    <function my_cuda_math_rule at 0x7f5cc13808c0>
 
 
 
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 ff6659b4d2..9f6e90c7ad 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
 =================
-**00:07.650** total execution time for **how_to_work_with_schedules** files:
+**00:07.373** total execution time for **how_to_work_with_schedules** files:
 
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)                 | 00:05.341 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)                 | 00:05.026 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)                     | 00:00.986 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)                     | 00:01.043 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)                     | 00:00.555 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)                               | 00:00.542 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)                               | 00:00.535 | 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_extern_op.py` (``extern_op.py``)                     | 00:00.116 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.055 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.049 | 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_tedd.py` (``tedd.py``)                               | 00:00.029 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``)               | 00:00.021 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``)               | 00:00.019 | 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 13908b1918..561b2f532f 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -343,7 +343,7 @@ The importing needs to happen before the tensorized GEMV being executed.
                  B: Buffer(B_2: Pointer(float32), float32, [512, 64], []),
                  C: Buffer(C_2: Pointer(float32), float32, [1024, 512], [])}
       buffer_map = {A_1: A, B_1: B, C_1: C} {
-      attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp9m2vzx82/input0.cc'\nsource_filename = \"/tmp/tmp9m2vzx82/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n  %7 = alloca float*, align 8\n  %8 = alloca float*, align 8\n  %9 = alloca floa [...]
+      attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp0b8qkn1u/input0.cc'\nsource_filename = \"/tmp/tmp0b8qkn1u/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n  %7 = alloca float*, align 8\n  %8 = alloca float*, align 8\n  %9 = alloca floa [...]
       for (i, 0, 1024) {
         for (j.outer: int32, 0, 32) {
           @tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
index e77273ec85..671b4b647c 100644
--- a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
 
 Computation times
 =================
-**00:27.455** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:26.589** total execution time for **topic_vta_tutorials_autotvm** files:
 
 +---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:27.449 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:26.582 | 0.0 MB |
 +---------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``)     | 00:00.006 | 0.0 MB |
 +---------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
index 3d98add499..859c2ce2c9 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -289,7 +289,7 @@ The compilation steps are:
       DeprecationWarning,
     /workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the  new recommended usage.
       relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
-    resnet18_v1 inference graph built in 31.70s!
+    resnet18_v1 inference graph built in 29.82s!
 
 
 
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 7af79c1f81..ec6e486667 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -333,7 +333,7 @@ The compilation steps are:
 
     /workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
       DeprecationWarning,
-    yolov3-tiny inference graph built in 20.16s!
+    yolov3-tiny inference graph built in 20.23s!
 
 
 
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 6476c30d66..aa1a74a8fe 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
 =================
-**01:44.215** total execution time for **topic_vta_tutorials_frontend** files:
+**01:42.683** total execution time for **topic_vta_tutorials_frontend** files:
 
 +------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)           | 00:52.496 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)           | 00:52.995 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:51.719 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:49.688 | 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 8231ef25c4..c85d4edcce 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
 =================
-**00:03.108** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.153** total execution time for **topic_vta_tutorials_optimize** files:
 
 +--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)         | 00:02.673 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)         | 00:02.714 | 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``) | 00:00.440 | 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 7e83f59ad3..917c9643bb 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
 =================
-**00:00.767** total execution time for **topic_vta_tutorials** files:
+**00:00.764** total execution time for **topic_vta_tutorials** files:
 
 +---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.413 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.408 | 0.0 MB |
 +---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.354 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.357 | 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 69aa0c496e..a24990e7c8 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -203,13 +203,6 @@ trials, we can load the best schedule from the log file and apply it.
 
 
 
-.. rst-class:: sphx-glr-script-out
-
- .. code-block:: none
-
-
-    *E
-
 
 
 
@@ -332,7 +325,7 @@ We build the binary and check its correctness and performance.
 
  .. code-block:: none
 
-    Execution time of this operator: 94.882 ms
+    Execution time of this operator: 93.327 ms
 
 
 
@@ -450,7 +443,7 @@ operations.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  33.236 seconds)
+   **Total running time of the script:** ( 1 minutes  16.007 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 89e7902fd6..b48792c4c7 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -450,16 +450,16 @@ reduce variance, we take 5 measurements and average them.
     waiting for device...
     device available
     Get devices for measurement successfully!
-    No: 1   GFLOPS: 9.50/9.50       result: MeasureResult(costs=(0.028269254,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6169953346252441, timestamp=1668611249.245705) [('tile_y', [-1, 4]), ('tile_x', [-1, 32])],None,52
-    No: 2   GFLOPS: 10.05/10.05     result: MeasureResult(costs=(0.026706745799999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.9295623302459717, timestamp=1668611250.5821307)       [('tile_y', [-1, 16]), ('tile_x', [-1, 128])],None,74
-    No: 3   GFLOPS: 1.66/10.05      result: MeasureResult(costs=(0.161746875,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7350432872772217, timestamp=1668611254.0759397)        [('tile_y', [-1, 8]), ('tile_x', [-1, 1])],None,3
-    No: 4   GFLOPS: 3.68/10.05      result: MeasureResult(costs=(0.072891678,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3188543319702148, timestamp=1668611256.1606019)        [('tile_y', [-1, 128]), ('tile_x', [-1, 16])],None,47
-    No: 5   GFLOPS: 2.95/10.05      result: MeasureResult(costs=(0.09090782359999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6086602210998535, timestamp=1668611257.922664) [('tile_y', [-1, 2]), ('tile_x', [-1, 8])],None,31
-    No: 6   GFLOPS: 2.86/10.05      result: MeasureResult(costs=(0.0937155482,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6676971912384033, timestamp=1668611259.5862784)       [('tile_y', [-1, 2]), ('tile_x', [-1, 16])],None,41
-    No: 7   GFLOPS: 3.61/10.05      result: MeasureResult(costs=(0.07428857520000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3442738056182861, timestamp=1668611260.944852) [('tile_y', [-1, 8]), ('tile_x', [-1, 8])],None,33
-    No: 8   GFLOPS: 13.75/13.75     result: MeasureResult(costs=(0.0195251974,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5363571643829346, timestamp=1668611261.464481)        [('tile_y', [-1, 128]), ('tile_x', [-1, 64])],None,67
-    No: 9   GFLOPS: 9.56/13.75      result: MeasureResult(costs=(0.028064372200000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6169466972351074, timestamp=1668611262.2148101)       [('tile_y', [-1, 512]), ('tile_x', [-1, 128])],None,79
-    No: 10  GFLOPS: 13.15/13.75     result: MeasureResult(costs=(0.0204108224,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5056636333465576, timestamp=1668611262.7110298)       [('tile_y', [-1, 128]), ('tile_x', [-1, 128])],None,77
+    No: 1   GFLOPS: 11.03/11.03     result: MeasureResult(costs=(0.024329743600000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5313427448272705, timestamp=1668617045.4020307)       [('tile_y', [-1, 1]), ('tile_x', [-1, 512])],None,90
+    No: 2   GFLOPS: 12.24/12.24     result: MeasureResult(costs=(0.0219322012,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5325038433074951, timestamp=1668617046.6605668)       [('tile_y', [-1, 8]), ('tile_x', [-1, 256])],None,83
+    No: 3   GFLOPS: 14.66/14.66     result: MeasureResult(costs=(0.0183090816,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7388677597045898, timestamp=1668617047.8500664)       [('tile_y', [-1, 64]), ('tile_x', [-1, 64])],None,66
+    No: 4   GFLOPS: 12.39/14.66     result: MeasureResult(costs=(0.021670452599999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.4895329475402832, timestamp=1668617048.365852)        [('tile_y', [-1, 256]), ('tile_x', [-1, 512])],None,98
+    No: 5   GFLOPS: 8.70/14.66      result: MeasureResult(costs=(0.030850067400000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.8019249439239502, timestamp=1668617049.2892187)       [('tile_y', [-1, 16]), ('tile_x', [-1, 64])],None,64
+    No: 6   GFLOPS: 12.55/14.66     result: MeasureResult(costs=(0.021383448000000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5027682781219482, timestamp=1668617049.800311)        [('tile_y', [-1, 256]), ('tile_x', [-1, 256])],None,88
+    No: 7   GFLOPS: 12.11/14.66     result: MeasureResult(costs=(0.0221694228,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.593656063079834, timestamp=1668617051.070341) [('tile_y', [-1, 1]), ('tile_x', [-1, 64])],None,60
+    No: 8   GFLOPS: 4.03/14.66      result: MeasureResult(costs=(0.0666180478,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2662608623504639, timestamp=1668617052.3394432)       [('tile_y', [-1, 4]), ('tile_x', [-1, 16])],None,42
+    No: 9   GFLOPS: 13.09/14.66     result: MeasureResult(costs=(0.0205115432,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.4462544918060303, timestamp=1668617052.900465)        [('tile_y', [-1, 4]), ('tile_x', [-1, 512])],None,92
+    No: 10  GFLOPS: 1.71/14.66      result: MeasureResult(costs=(0.15705507219999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.621229410171509, timestamp=1668617055.5771248) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
 
 
 
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 4d21e88764..f161addcad 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -320,7 +320,7 @@ standard deviation.
 
  .. code-block:: none
 
-    {'mean': 515.9832460300095, 'median': 516.074852450015, 'std': 2.1019770271666354}
+    {'mean': 516.8028887700029, 'median': 516.7933151499938, 'std': 1.8442027952596247}
 
 
 
@@ -554,29 +554,30 @@ 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:   17.62/  17.62 GFLOPS | Progress: (4/20) | 9.23 s
    [Task  1/25]  Current/Best:   22.20/  22.93 GFLOPS | Progress: (8/20) | 11.31 s
    [Task  1/25]  Current/Best:    8.53/  22.93 GFLOPS | Progress: (12/20) | 14.39 s
    [Task  1/25]  Current/Best:   13.52/  22.93 GFLOPS | Progress: (16/20) | 16.87 s
    [Task  1/25]  Current/Best:    9.93/  22.93 GFLOPS | Progress: (20/20) | 19.27 s Done.
-
    [Task  2/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  2/25]  Current/Best:   18.42/  19.63 GFLOPS | Progress: (4/20) | 2.67 s
    [Task  2/25]  Current/Best:   12.58/  19.63 GFLOPS | Progress: (8/20) | 3.74 s
    [Task  2/25]  Current/Best:   13.59/  19.63 GFLOPS | Progress: (12/20) | 5.36 s
    [Task  2/25]  Current/Best:    6.25/  19.63 GFLOPS | Progress: (16/20) | 7.11 s
    [Task  2/25]  Current/Best:   12.95/  20.04 GFLOPS | Progress: (20/20) | 8.42 s Done.
-
    [Task  3/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  3/25]  Current/Best:   17.03/  17.03 GFLOPS | Progress: (4/20) | 3.31 s
    [Task  3/25]  Current/Best:    5.74/  20.14 GFLOPS | Progress: (8/20) | 5.95 s
    [Task  3/25]  Current/Best:   15.87/  23.62 GFLOPS | Progress: (12/20) | 8.30 s
    [Task  3/25]  Current/Best:   17.11/  23.62 GFLOPS | Progress: (16/20) | 10.95 s
    [Task  3/25]  Current/Best:   17.90/  23.62 GFLOPS | Progress: (20/20) | 13.52 s Done.
-
    [Task  4/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  4/25]  Current/Best:    8.44/  18.73 GFLOPS | Progress: (4/20) | 3.59 s
    [Task  4/25]  Current/Best:    5.10/  18.73 GFLOPS | Progress: (8/20) | 11.01 s
    [Task  4/25]  Current/Best:   15.76/  18.73 GFLOPS | Progress: (12/20) | 12.91 s
    [Task  4/25]  Current/Best:   11.95/  18.73 GFLOPS | Progress: (16/20) | 14.61 s
    [Task  4/25]  Current/Best:   11.70/  18.73 GFLOPS | Progress: (20/20) | 17.29 s Done.
-
    [Task  5/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  5/25]  Current/Best:    6.82/  19.14 GFLOPS | Progress: (4/20) | 3.05 s
    [Task  5/25]  Current/Best:    4.12/  19.14 GFLOPS | Progress: (8/20) | 4.96 s
    [Task  5/25]  Current/Best:   18.45/  19.14 GFLOPS | Progress: (12/20) | 6.41 s
    [Task  5/25]  Current/Best:    6.80/  19.14 GFLOPS | Progress: (16/20) | 8.18 s
    [Task  5/25]  Current/Best:    6.72/  19.14 GFLOPS | Progress: (20/20) | 10.05 s Done.
-
    [Task  6/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  6/25]  Current/Best:   16.23/  16.23 GFLOPS | Progress: (4/20) | 4.04 s
    [Task  6/25]  Current/Best:   20.57/  20.57 GFLOPS | Progress: (8/20) | 5.80 s
    [Task  6/25]  Current/Best:   14.70/  20.57 GFLOPS | Progress: (12/20) | 8.75 s
    [Task  6/25]  Current/Best:   12.13/  20.57 GFLOPS | Progress: (16/20) | 11.07 s
    [Task  6/25]  Current/Best:   17.89/  20.57 GFLOPS | Progress: (20/20) | 12.82 s Done.
-
    [Task  7/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  7/25]  Current/Best:   11.14/  16.33 GFLOPS | Progress: (4/20) | 4.95 s
    [Task  7/25]  Current/Best:   15.37/  16.66 GFLOPS | Progress: (8/20) | 6.95 s
    [Task  7/25]  Current/Best:   15.60/  16.66 GFLOPS | Progress: (12/20) | 9.50 s
    [Task  7/25]  Current/Best:   17.45/  17.45 GFLOPS | Progress: (16/20) | 12.01 s
    [Task  7/25]  Current/Best:   13.67/  20.09 GFLOPS | Progress: (20/20) | 13.81 s Done.
-
    [Task  8/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  8/25]  Current/Best:    5.35/  15.05 GFLOPS | Progress: (4/20) | 4.50 s
    [Task  8/25]  Current/Best:   16.11/  16.11 GFLOPS | Progress: (8/20) | 15.62 s
    [Task  8/25]  Current/Best:    2.77/  16.70 GFLOPS | Progress: (12/20) | 21.04 s
    [Task  8/25]  Current/Best:   15.39/  16.70 GFLOPS | Progress: (16/20) | 28.78 s
    [Task  8/25]  Current/Best:   11.97/  16.70 GFLOPS | Progress: (20/20) | 31.86 s
    [Task  9/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  9/25]  Current/Best:   13.79/  13.79 GFLOPS | Progress: (4/20) | 5.40 s
    [Task  9/25]  Current/Best:   10.91/  17.79 GFLOPS | Progress: (8/20) | 11.29 s
    [Task  9/25]  Current/Best:   12.27/  22.39 GFLOPS | Progress: (12/20) | 15.97 s
    [Task  9/25]  Current/Best:   10.27/  22.39 GFLOPS | Progress: (16/20) | 20.20 s
    [Task  9/25]  Current/Best:   17.87/  22.39 GFLOPS | Progress: (20/
 20) | 27.52 s Done.
-
    [Task 10/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 10/25]  Current/Best:   18.03/  19.55 GFLOPS | Progress: (4/20) | 2.93 s
    [Task 10/25]  Current/Best:    8.00/  19.55 GFLOPS | Progress: (8/20) | 4.37 s
    [Task 10/25]  Current/Best:   17.89/  19.55 GFLOPS | Progress: (12/20) | 6.14 s
    [Task 10/25]  Current/Best:    1.61/  19.55 GFLOPS | Progress: (16/20) | 8.15 s
    [Task 10/25]  Current/Best:    9.84/  19.55 GFLOPS | Progress: (20/20) | 11.03 s Done.
-
    [Task 11/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 11/25]  Current/Best:   18.43/  21.07 GFLOPS | Progress: (4/20) | 3.65 s
    [Task 11/25]  Current/Best:   17.97/  21.07 GFLOPS | Progress: (8/20) | 6.36 s
    [Task 11/25]  Current/Best:   18.34/  21.07 GFLOPS | Progress: (12/20) | 8.98 s
    [Task 11/25]  Current/Best:    6.28/  22.11 GFLOPS | Progress: (16/20) | 10.99 s
    [Task 11/25]  Current/Best:    8.99/  22.11 GFLOPS | Progress: (20/20) | 12.74 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/  14.96 GFLOPS | Progress: (4/20) | 7.59 s
    [Task 12/25]  Current/Best:   13.11/  14.96 GFLOPS | Progress: (8/20) | 10.25 s
    [Task 12/25]  Current/Best:    7.19/  16.25 GFLOPS | Progress: (12/20) | 12.80 s
    [Task 12/25]  Current/Best:   13.40/  16.83 GFLOPS | Progress: (16/20) | 15.64 s
    [Task 12/25]  Current/Best:   18.27/  18.27 GFLOPS | Progress: (20/20) | 18.61 s Done.
-
    [Task 13/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 13/25]  Current/Best:   15.64/  20.70 GFLOPS | Progress: (4/20) | 3.65 s
    [Task 13/25]  Current/Best:    6.99/  20.70 GFLOPS | Progress: (8/20) | 7.70 s
    [Task 13/25]  Current/Best:   20.14/  20.70 GFLOPS | Progress: (12/20) | 9.74 s
    [Task 13/25]  Current/Best:   18.66/  20.70 GFLOPS | Progress: (16/20) | 12.46 s
    [Task 13/25]  Current/Best:   17.19/  20.70 GFLOPS | Progress: (20/20) | 14.71 s Done.
-
    [Task 14/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 14/25]  Current/Best:   15.95/  16.88 GFLOPS | Progress: (4/20) | 4.73 s
    [Task 14/25]  Current/Best:   10.84/  16.88 GFLOPS | Progress: (8/20) | 6.69 s
    [Task 14/25]  Current/Best:    4.59/  17.93 GFLOPS | Progress: (12/20) | 9.66 s
    [Task 14/25]  Current/Best:   16.22/  17.93 GFLOPS | Progress: (16/20) | 13.34 s
    [Task 14/25]  Current/Best:   13.15/  17.93 GFLOPS | Progress: (20/20) | 15.26 s Done.
-
    [Task 15/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 15/25]  Current/Best:   19.42/  20.85 GFLOPS | Progress: (4/20) | 3.30 s
    [Task 15/25]  Current/Best:   12.02/  20.85 GFLOPS | Progress: (8/20) | 8.36 s Done.
-
    [Task 15/25]  Current/Best:   16.04/  20.85 GFLOPS | Progress: (12/20) | 10.34 s
    [Task 15/25]  Current/Best:   12.46/  20.85 GFLOPS | Progress: (16/20) | 15.89 s
    [Task 15/25]  Current/Best:   13.47/  21.22 GFLOPS | Progress: (20/20) | 17.92 s
    [Task 16/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 16/25]  Current/Best:    8.65/  18.84 GFLOPS | Progress: (4/20) | 2.79 s
    [Task 16/25]  Current/Best:   15.93/  19.96 GFLOPS | Progress: (8/20) | 4.03 s
    [Task 16/25]  Current/Best:   15.47/  19.96 GFLOPS | Progress: (12/20) | 5.24 s
    [Task 16/25]  Current/Best:   18.49/  19.96 GFLOPS | Progress: (16/20) | 6.97 s
    [Task 16/25]  Current/Best:    6.75/  21.17 GFLOPS | Progress: (20/20) | 9.72 s Done.
-
    [Task 17/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 17/25]  Current/Best:   10.18/  15.89 GFLOPS | Progress: (4/20) | 4.54 s
    [Task 17/25]  Current/Best:   20.77/  23.74 GFLOPS | Progress: (8/20) | 6.15 s
    [Task 17/25]  Current/Best:    9.72/  23.74 GFLOPS | Progress: (12/20) | 8.51 s
    [Task 17/25]  Current/Best:   17.01/  23.74 GFLOPS | Progress: (16/20) | 10.72 s
    [Task 17/25]  Current/Best:   10.42/  23.74 GFLOPS | Progress: (20/20) | 13.24 s Done.
-
    [Task 18/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 18/25]  Current/Best:   14.95/  19.22 GFLOPS | Progress: (4/20) | 4.99 s
    [Task 18/25]  Current/Best:   17.63/  19.22 GFLOPS | Progress: (8/20) | 6.65 s
    [Task 18/25]  Current/Best:    5.77/  19.22 GFLOPS | Progress: (12/20) | 13.28 s
    [Task 18/25]  Current/Best:    9.45/  19.22 GFLOPS | Progress: (16/20) | 17.04 s
    [Task 18/25]  Current/Best:   16.10/  19.22 GFLOPS | Progress: (20/20) | 19.12 s Done.
-
    [Task 19/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 19/25]  Current/Best:   13.38/  18.27 GFLOPS | Progress: (4/20) | 6.64 s
    [Task 19/25]  Current/Best:   19.57/  19.57 GFLOPS | Progress: (8/20) | 9.94 s
    [Task 19/25]  Current/Best:    2.68/  19.57 GFLOPS | Progress: (12/20) | 14.00 s
    [Task 19/25]  Current/Best:    8.18/  20.74 GFLOPS | Progress: (16/20) | 17.23 s
    [Task 19/25]  Current/Best:   10.09/  20.74 GFLOPS | Progress: (20/20) | 19.62 s Done.
-
    [Task 20/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 20/25]  Current/Best:    7.49/   7.49 GFLOPS | Progress: (4/20) | 3.45 s
    [Task 20/25]  Current/Best:   16.03/  16.76 GFLOPS | Progress: (8/20) | 9.41 s
    [Task 20/25]  Current/Best:    4.17/  16.76 GFLOPS | Progress: (12/20) | 12.24 s
    [Task 20/25]  Current/Best:   10.20/  16.76 GFLOPS | Progress: (16/20) | 14.23 s
    [Task 20/25]  Current/Best:    5.07/  16.76 GFLOPS | Progress: (20/20) | 17.55 s
    [Task 21/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 21/25]  Current/Best:   10.31/  13.11 GFLOPS | Progress: (4/20) | 4.96 s Done.
+
    [Task  1/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  1/25]  Current/Best:   14.83/  17.52 GFLOPS | Progress: (4/20) | 6.94 s
    [Task  1/25]  Current/Best:   22.90/  22.90 GFLOPS | Progress: (8/20) | 13.12 s
    [Task  1/25]  Current/Best:    5.64/  22.90 GFLOPS | Progress: (12/20) | 16.27 s
    [Task  1/25]  Current/Best:    5.76/  22.90 GFLOPS | Progress: (16/20) | 19.33 s
    [Task  1/25]  Current/Best:    5.27/  22.90 GFLOPS | Progress: (20/20) | 23.12 s Done.
+
    [Task  2/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  2/25]  Current/Best:   21.38/  21.38 GFLOPS | Progress: (4/20) | 2.70 s
    [Task  2/25]  Current/Best:   13.71/  21.38 GFLOPS | Progress: (8/20) | 4.44 s
    [Task  2/25]  Current/Best:    7.99/  21.38 GFLOPS | Progress: (12/20) | 5.51 s
    [Task  2/25]  Current/Best:   13.04/  21.38 GFLOPS | Progress: (16/20) | 7.34 s
    [Task  2/25]  Current/Best:   12.92/  21.38 GFLOPS | Progress: (20/20) | 9.32 s Done.
+
    [Task  3/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  3/25]  Current/Best:   10.70/  21.14 GFLOPS | Progress: (4/20) | 3.45 s
    [Task  3/25]  Current/Best:    6.22/  21.14 GFLOPS | Progress: (8/20) | 6.03 s
    [Task  3/25]  Current/Best:   15.77/  24.11 GFLOPS | Progress: (12/20) | 7.70 s
    [Task  3/25]  Current/Best:    7.64/  24.11 GFLOPS | Progress: (16/20) | 10.06 s
    [Task  3/25]  Current/Best:    5.62/  24.11 GFLOPS | Progress: (20/20) | 12.75 s Done.
+
    [Task  4/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  4/25]  Current/Best:   16.29/  16.29 GFLOPS | Progress: (4/20) | 6.83 s
    [Task  4/25]  Current/Best:    7.81/  16.82 GFLOPS | Progress: (8/20) | 9.05 s
    [Task  4/25]  Current/Best:   11.80/  16.82 GFLOPS | Progress: (12/20) | 10.93 s
    [Task  4/25]  Current/Best:    8.10/  20.87 GFLOPS | Progress: (16/20) | 12.89 s
    [Task  4/25]  Current/Best:   10.30/  20.87 GFLOPS | Progress: (20/20) | 14.43 s Done.
+
    [Task  5/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  5/25]  Current/Best:   16.87/  19.70 GFLOPS | Progress: (4/20) | 2.86 s
    [Task  5/25]  Current/Best:   15.38/  19.70 GFLOPS | Progress: (8/20) | 4.70 s
    [Task  5/25]  Current/Best:   20.58/  20.58 GFLOPS | Progress: (12/20) | 6.48 s
    [Task  5/25]  Current/Best:   18.06/  20.58 GFLOPS | Progress: (16/20) | 8.59 s
    [Task  5/25]  Current/Best:   13.01/  20.58 GFLOPS | Progress: (20/20) | 10.67 s Done.
+
    [Task  6/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  6/25]  Current/Best:   14.33/  14.33 GFLOPS | Progress: (4/20) | 5.51 s
    [Task  6/25]  Current/Best:    4.06/  16.30 GFLOPS | Progress: (8/20) | 9.09 s
    [Task  6/25]  Current/Best:   13.88/  18.00 GFLOPS | Progress: (12/20) | 11.51 s
    [Task  6/25]  Current/Best:    5.40/  18.00 GFLOPS | Progress: (16/20) | 18.65 s
    [Task  6/25]  Current/Best:   18.29/  18.29 GFLOPS | Progress: (20/20) | 20.96 s Done.
+
    [Task  7/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  7/25]  Current/Best:   15.20/  15.20 GFLOPS | Progress: (4/20) | 3.46 s
    [Task  7/25]  Current/Best:    6.23/  19.30 GFLOPS | Progress: (8/20) | 5.28 s
    [Task  7/25]  Current/Best:    5.76/  19.56 GFLOPS | Progress: (12/20) | 7.38 s
    [Task  7/25]  Current/Best:   12.47/  19.56 GFLOPS | Progress: (16/20) | 9.66 s
    [Task  7/25]  Current/Best:   12.35/  19.56 GFLOPS | Progress: (20/20) | 12.21 s Done.
+
    [Task  8/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  8/25]  Current/Best:   11.96/  17.28 GFLOPS | Progress: (4/20) | 4.86 s
    [Task  8/25]  Current/Best:   11.46/  17.28 GFLOPS | Progress: (8/20) | 12.13 s
    [Task  8/25]  Current/Best:    4.75/  17.28 GFLOPS | Progress: (12/20) | 18.56 s
    [Task  8/25]  Current/Best:   11.91/  17.37 GFLOPS | Progress: (16/20) | 21.37 s
    [Task  8/25]  Current/Best:    7.64/  17.37 GFLOPS | Progress: (20/20) | 25.35 s Done.
+
    [Task  9/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  9/25]  Current/Best:    1.89/  12.86 GFLOPS | Progress: (4/20) | 3.63 s
    [Task  9/25]  Current/Best:   11.89/  16.17 GFLOPS | Progress: (8/20) | 5.42 s
    [Task  9/25]  Current/Best:   12.02/  16.17 GFLOPS | Progress: (12/20) | 10.23 s
    [Task  9/25]  Current/Best:   15.31/  17.52 GFLOPS | Progress: (16/20) | 12.62 s
    [Task  9/25]  Current/Best:   20.09/  20.09 GFLOPS | Progress: (20/20) | 14.54 s Done.
+
    [Task 10/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 10/25]  Current/Best:   14.32/  14.85 GFLOPS | Progress: (4/20) | 3.45 s
    [Task 10/25]  Current/Best:   11.53/  18.58 GFLOPS | Progress: (8/20) | 4.76 s
    [Task 10/25]  Current/Best:    8.58/  18.58 GFLOPS | Progress: (12/20) | 6.32 s
    [Task 10/25]  Current/Best:   14.22/  18.58 GFLOPS | Progress: (16/20) | 8.33 s
    [Task 10/25]  Current/Best:   11.08/  18.58 GFLOPS | Progress: (20/20) | 9.96 s Done.
+
    [Task 11/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 11/25]  Current/Best:    3.12/  17.00 GFLOPS | Progress: (4/20) | 4.80 s
    [Task 11/25]  Current/Best:   16.82/  18.12 GFLOPS | Progress: (8/20) | 7.19 s
    [Task 11/25]  Current/Best:   12.34/  18.12 GFLOPS | Progress: (12/20) | 10.09 s
    [Task 11/25]  Current/Best:    1.57/  18.12 GFLOPS | Progress: (16/20) | 13.71 s
    [Task 11/25]  Current/Best:   20.54/  20.54 GFLOPS | Progress: (20/20) | 16.01 s Done.
+
    [Task 12/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 12/25]  Current/Best:    9.56/  15.70 GFLOPS | Progress: (4/20) | 10.39 s
    [Task 12/25]  Current/Best:   10.31/  18.76 GFLOPS | Progress: (8/20) | 12.35 s
    [Task 12/25]  Current/Best:   11.86/  18.76 GFLOPS | Progress: (12/20) | 17.78 s
    [Task 12/25]  Current/Best:    7.60/  18.76 GFLOPS | Progress: (16/20) | 24.01 s
    [Task 12/25]  Current/Best:   13.71/  18.76 GFLOPS | Progress: (20/20) | 26.60 s Done.
+
    [Task 13/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 13/25]  Current/Best:    5.12/  20.59 GFLOPS | Progress: (4/20) | 4.05 s
    [Task 13/25]  Current/Best:    6.12/  20.67 GFLOPS | Progress: (8/20) | 7.20 s
    [Task 13/25]  Current/Best:   12.08/  20.67 GFLOPS | Progress: (12/20) | 9.34 s
    [Task 13/25]  Current/Best:   14.34/  20.67 GFLOPS | Progress: (16/20) | 11.51 s
    [Task 13/25]  Current/Best:    9.25/  21.71 GFLOPS | Progress: (20/20) | 14.90 s Done.
+
    [Task 14/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 14/25]  Current/Best:    7.44/  11.29 GFLOPS | Progress: (4/20) | 6.25 s
    [Task 14/25]  Current/Best:   12.48/  12.48 GFLOPS | Progress: (8/20) | 8.62 s
    [Task 14/25]  Current/Best:   11.81/  13.03 GFLOPS | Progress: (12/20) | 13.01 s
    [Task 14/25]  Current/Best:   12.45/  13.03 GFLOPS | Progress: (16/20) | 18.03 s
    [Task 14/25]  Current/Best:   14.63/  14.63 GFLOPS | Progress: (20/20) | 23.32 s
    [Task 15/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 15/25]  Current/Best:   13.92/  16.77 GFLOPS | Progress: (4/20) | 3.48 s
    [Task 15/25]  Current/Best:   13.28/  19.09 GFLOPS | Progress: (8/20) | 5.91 s
    [Task 15/25]  Current/Best:   20.75/  20.75 GFLOPS | Progress: (12/20) | 7.20 s
    [Task 15/25]  Current/Best:   15.44/  20.75 GFLOPS | Progress: (16/20) | 9.49 s
    [Task 15/25]  Current/Best:   15.76/  20.75 GFLOPS | Progress: (20/20) 
 | 10.71 s
    [Task 16/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 16/25]  Current/Best:    5.97/  14.01 GFLOPS | Progress: (4/20) | 3.62 s Done.
      Done.
-
    [Task 21/25]  Current/Best:   14.77/  21.91 GFLOPS | Progress: (8/20) | 6.74 s
    [Task 21/25]  Current/Best:   12.92/  21.91 GFLOPS | Progress: (12/20) | 9.14 s
    [Task 21/25]  Current/Best:   15.33/  21.91 GFLOPS | Progress: (16/20) | 11.08 s
    [Task 21/25]  Current/Best:    8.90/  21.91 GFLOPS | Progress: (20/20) | 13.09 s
    [Task 22/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 22/25]  Current/Best:    4.44/   7.62 GFLOPS | Progress: (4/20) | 4.19 s
    [Task 22/25]  Current/Best:   14.70/  17.83 GFLOPS | Progress: (8/20) | 6.71 s
    [Task 22/25]  Current/Best:   12.40/  20.78 GFLOPS | Progress: (12/20) | 8.56 s
    [Task 22/25]  Current/Best:   20.28/  20.78 GFLOPS | Progress: (16/20) | 11.73 s
    [Task 22/25]  Current/Best:    7.02/  20.78 GFLOPS | Progress: (20/20) | 14.21 s Done.
-
    [Task 23/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 23/25]  Current/Best:    9.41/  19.74 GFLOPS | Progress: (4/20) | 4.17 s
    [Task 23/25]  Current/Best:    9.27/  19.74 GFLOPS | Progress: (8/20) | 6.75 s
    [Task 23/25]  Current/Best:   23.76/  23.76 GFLOPS | Progress: (12/20) | 8.81 s
    [Task 23/25]  Current/Best:    3.08/  23.76 GFLOPS | Progress: (16/20) | 11.64 s
    [Task 23/25]  Current/Best:   12.00/  23.76 GFLOPS | Progress: (20/20) | 14.27 s Done.
-
    [Task 24/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 24/25]  Current/Best:    2.27/   6.50 GFLOPS | Progress: (4/20) | 12.26 s
    [Task 24/25]  Current/Best:    7.90/   7.90 GFLOPS | Progress: (8/20) | 23.59 s
    [Task 24/25]  Current/Best:    6.66/   7.90 GFLOPS | Progress: (12/20) | 34.44 s
    [Task 24/25]  Current/Best:    8.96/   8.96 GFLOPS | Progress: (16/20) | 45.11 s
    [Task 24/25]  Current/Best:    7.19/   8.96 GFLOPS | Progress: (20/20) | 55.58 s
    [Task 25/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 25/25]  Current/Best:    9.06/   9.06 GFLOPS | Progress: (4/20) | 11.59 s
    [Task 25/25]  Current/Best:    3.50/   9.17 GFLOPS | Progress: (8/20) | 22.30 s
    [Task 25/25]  Current/Best:    7.17/   9.17 GFLOPS | Progress: (12/20) | 24.08 s
    [Task 25/25]  Current/Best:    7.55/   9.17 GFLOPS | Progress: (16/20) | 34.79 s
    [Task 25/25]  Current/Best:    4.37/   9.17 GFLOPS | Progress: (2
 0/20) | 36.67 s
+
    [Task 16/25]  Current/Best:   15.54/  20.34 GFLOPS | Progress: (8/20) | 6.49 s
    [Task 16/25]  Current/Best:   19.30/  20.34 GFLOPS | Progress: (12/20) | 8.06 s
    [Task 16/25]  Current/Best:   14.24/  20.34 GFLOPS | Progress: (16/20) | 10.58 s
    [Task 16/25]  Current/Best:    4.57/  20.34 GFLOPS | Progress: (20/20) | 12.09 s Done.
+
    [Task 17/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 17/25]  Current/Best:   15.16/  18.26 GFLOPS | Progress: (4/20) | 3.45 s
    [Task 17/25]  Current/Best:   17.30/  20.30 GFLOPS | Progress: (8/20) | 5.45 s
    [Task 17/25]  Current/Best:   18.28/  20.30 GFLOPS | Progress: (12/20) | 7.76 s
    [Task 17/25]  Current/Best:   22.24/  22.24 GFLOPS | Progress: (16/20) | 9.28 s
    [Task 17/25]  Current/Best:   15.56/  22.24 GFLOPS | Progress: (20/20) | 11.75 s Done.
+
    [Task 18/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 18/25]  Current/Best:   15.15/  15.15 GFLOPS | Progress: (4/20) | 6.83 s
    [Task 18/25]  Current/Best:    9.94/  17.98 GFLOPS | Progress: (8/20) | 11.68 s
    [Task 18/25]  Current/Best:   10.07/  17.98 GFLOPS | Progress: (12/20) | 15.33 s
    [Task 18/25]  Current/Best:   11.48/  17.98 GFLOPS | Progress: (16/20) | 18.40 s
    [Task 18/25]  Current/Best:    5.07/  19.22 GFLOPS | Progress: (20/20) | 20.34 s Done.
+
    [Task 19/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 19/25]  Current/Best:    8.42/  21.05 GFLOPS | Progress: (4/20) | 6.45 s
    [Task 19/25]  Current/Best:   19.58/  21.05 GFLOPS | Progress: (8/20) | 9.99 s
    [Task 19/25]  Current/Best:   18.15/  21.05 GFLOPS | Progress: (12/20) | 12.09 s
    [Task 19/25]  Current/Best:   16.87/  21.05 GFLOPS | Progress: (16/20) | 15.33 s
    [Task 19/25]  Current/Best:    9.35/  21.05 GFLOPS | Progress: (20/20) | 19.20 s Done.
+
    [Task 20/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 20/25]  Current/Best:    9.72/  17.55 GFLOPS | Progress: (4/20) | 3.03 s
    [Task 20/25]  Current/Best:   13.98/  17.55 GFLOPS | Progress: (8/20) | 6.28 s
    [Task 20/25]  Current/Best:   10.40/  17.55 GFLOPS | Progress: (12/20) | 8.90 s
    [Task 20/25]  Current/Best:   17.84/  20.50 GFLOPS | Progress: (16/20) | 11.69 s
    [Task 20/25]  Current/Best:   15.56/  20.50 GFLOPS | Progress: (20/20) | 15.71 s
    [Task 21/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
    [Task 21/25]  Current/Best:    2.52/  12.52 GFLOPS | Progress: (4/20) | 3.34 s
    [Task 21/25]  Current/Best:   17.76/  17.76 GFLOPS | Progress: (8/20) | 7.84 s
    [Task 21/25]  Current/Best:    5.25/  17.76 GFLOPS | Progress: (12/20) | 9.86 s
    [Task 21/25]  Current/Best:    2.68/  21.66 GFLOPS | Progress: (16/20) | 12.26 s
    [Task 21/25]  Current/Best:   13.50/  21.66 GFLOPS | Progress: (20/20) | 13.87 s
    [Task 22/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 22/25]  Current/Best:    5.19/  12.99 GFLOPS | Progress: (4/20) | 3.85 s
    [Task 22/25]  Current/Best:    7.63/  16.16 GFLOPS | Progress: (8/20) | 5.67 s
    [Task 22/25]  Current/Best:    9.04/  18.37 GFLOPS | Progress: (12/20) | 8.13 s
    [Task 22/25]  Current/Best:   10.87/  18.37 GFLOPS | Progress: (16/20) | 11.44 s
    [Task 22/25]  Current/Best:    7.64/  18.37 GFLOPS | Progress: (20/20) | 13.54 s Done.
+
    [Task 23/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 23/25]  Current/Best:    1.55/  20.48 GFLOPS | Progress: (4/20) | 5.00 s
    [Task 23/25]  Current/Best:    5.36/  23.62 GFLOPS | Progress: (8/20) | 9.23 s
    [Task 23/25]  Current/Best:   11.24/  23.62 GFLOPS | Progress: (12/20) | 12.45 s
    [Task 23/25]  Current/Best:    8.43/  23.62 GFLOPS | Progress: (16/20) | 15.74 s
    [Task 23/25]  Current/Best:   11.42/  23.62 GFLOPS | Progress: (20/20) | 19.04 s Done.
+
    [Task 24/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 24/25]  Current/Best:    5.51/   5.51 GFLOPS | Progress: (4/20) | 4.97 s
    [Task 24/25]  Current/Best:    3.99/   5.51 GFLOPS | Progress: (8/20) | 15.70 s
    [Task 24/25]  Current/Best:    3.49/   8.12 GFLOPS | Progress: (12/20) | 26.45 s
    [Task 24/25]  Current/Best:    6.96/   8.12 GFLOPS | Progress: (16/20) | 37.16 s
    [Task 24/25]  Current/Best:    1.07/   8.12 GFLOPS | Progress: (20/20) | 44.66 s
    [Task 25/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
    [Task 25/25]  Current/Best:    3.52/   5.27 GFLOPS | Progress: (4/20) | 2.61 s
    [Task 25/25]  Current/Best:    8.89/   8.89 GFLOPS | Progress: (8/20) | 13.29 s
    [Task 25/25]  Current/Best:    3.63/   8.92 GFLOPS | Progress: (12/20) | 24.01 s
    [Task 25/25]  Current/Best:    1.51/   8.92 GFLOPS | Progress: (16/20) | 26.99 s
    [Task 25/25]  Current/Best:    5.81/   8.92 GFLOPS | Progress: (20/20) | 28.02 s
 
 
 
@@ -672,8 +673,8 @@ Verify that the optimized model runs and produces the same results:
 
  .. code-block:: none
 
-    class='n02123045 tabby, tabby cat' with probability=0.621103
-    class='n02123159 tiger cat' with probability=0.356379
+    class='n02123045 tabby, tabby cat' with probability=0.621104
+    class='n02123159 tiger cat' with probability=0.356378
     class='n02124075 Egyptian cat' with probability=0.019712
     class='n02129604 tiger, Panthera tigris' with probability=0.001215
     class='n04040759 radiator' with probability=0.000262
@@ -730,8 +731,8 @@ improvement in comparing the optimized model to the unoptimized model.
 
  .. code-block:: none
 
-    optimized: {'mean': 417.24817383000754, 'median': 416.0994904000063, 'std': 3.345817977638771}
-    unoptimized: {'mean': 515.9832460300095, 'median': 516.074852450015, 'std': 2.1019770271666354}
+    optimized: {'mean': 410.15801464000106, 'median': 408.6431573000027, 'std': 3.983016703746832}
+    unoptimized: {'mean': 516.8028887700029, 'median': 516.7933151499938, 'std': 1.8442027952596247}
 
 
 
@@ -754,7 +755,7 @@ profiling/benchmarking.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 11 minutes  9.688 seconds)
+   **Total running time of the script:** ( 10 minutes  53.937 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 3734300c53..8c7a73aa71 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -270,7 +270,7 @@ device and returns the measured cost. Network overhead is excluded.
 
  .. code-block:: none
 
-    1.137e-07 secs/op
+    1.227e-07 secs/op
 
 
 
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 10a4589546..5d7dfc97f2 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -260,7 +260,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
 
  .. code-block:: none
 
-    [stage(a, placeholder(a, 0x2134c3f0)), stage(b, placeholder(b, 0x21ee7aa0)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(mi [...]
+    [stage(a, placeholder(a, 0x22ef0670)), stage(b, placeholder(b, 0xe875ed0)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min [...]
 
 
 
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index 51ea4ccf32..a959ae05b7 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,24 +5,24 @@
 
 Computation times
 =================
-**14:44.179** total execution time for **tutorial** files:
+**14:03.663** total execution time for **tutorial** files:
 
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)                 | 11:09.688 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)                 | 10:53.937 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:33.236 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:16.007 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)     | 01:02.680 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)     | 01:01.084 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)                 | 00:38.658 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)                 | 00:35.950 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)               | 00:18.300 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)               | 00:15.132 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)                               | 00:00.810 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)                               | 00:00.771 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)       | 00:00.644 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)       | 00:00.628 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.154 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.145 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``)                           | 00:00.005 | 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 604eeab4e7..bcf3e2af07 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -294,7 +294,7 @@ helper function to run a profile of the TVM generated code.
 
  .. code-block:: none
 
-    Numpy running time: 0.000008
+    Numpy running time: 0.000007
     naive: 0.000007
 
 
@@ -393,7 +393,7 @@ compile and run this new schedule with the parallel operation applied:
 
  .. code-block:: none
 
-    parallel: 0.000008
+    parallel: 0.000007
 
 
 
@@ -499,10 +499,10 @@ We can now compare the different schedules
  .. code-block:: none
 
                 Operator                  Timing             Performance
-                   numpy    7.648709997738479e-06                    1.0
-                   naive              6.6648e-06      0.8713626221899647
-                parallel              8.3591e-06       1.092877099860181
-                  vector    2.4603500000000003e-05     3.216686213397371
+                   numpy    7.26831000065431e-06                     1.0
+                   naive    6.705600000000001e-06     0.9225803521583898
+                parallel              6.9417e-06      0.9550638318089201
+                  vector             2.45513e-05      3.3778553746042523
 
 
 
@@ -923,7 +923,7 @@ matrix multiplication.
 
  .. code-block:: none
 
-    Numpy running time: 0.018212
+    Numpy running time: 0.018680
 
 
 
@@ -981,7 +981,7 @@ optimizations.
 
  .. code-block:: none
 
-    none: 3.540408
+    none: 3.420528
 
 
 
@@ -1083,7 +1083,7 @@ schedule.
 
  .. code-block:: none
 
-    blocking: 0.299061
+    blocking: 0.298977
 
 
 
@@ -1178,7 +1178,7 @@ already cache friendly from our previous optimizations.
 
  .. code-block:: none
 
-    vectorization: 0.337274
+    vectorization: 0.333744
     @main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
       attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
       buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1251,7 +1251,7 @@ more cache friendly.
 
  .. code-block:: none
 
-    loop permutation: 0.118992
+    loop permutation: 0.117542
     @main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
       attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
       buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1349,7 +1349,7 @@ optimized schedule.
 
  .. code-block:: none
 
-    array packing: 0.109797
+    array packing: 0.108424
     @main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
       attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
       buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1441,7 +1441,7 @@ to `C` when all the block results are ready.
 
  .. code-block:: none
 
-    block caching: 0.110635
+    block caching: 0.110747
     @main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
       attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
       buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1526,7 +1526,7 @@ of thread-level parallelization.
 
  .. code-block:: none
 
-    parallelization: 0.144369
+    parallelization: 0.146593
     @main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
       attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
       buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1606,13 +1606,13 @@ working, we can compare the results.
  .. code-block:: none
 
                 Operator                  Timing             Performance
-                    none      3.5404082826999996                     1.0
-                blocking     0.29906072260000005     0.08447068776257896
-           vectorization            0.3372738984      0.0952641253405912
-        loop permutation     0.11899243670000001     0.03360980632698485
-           array packing     0.10979653869999999     0.03101239459768367
-           block caching             0.110635423    0.031249340235874376
-         parallelization     0.14436925309999998    0.040777571842618265
+                    none            3.4205275692                     1.0
+                blocking     0.29897708349999996     0.08740671649371484
+           vectorization             0.333743835     0.09757086538497238
+        loop permutation            0.1175421273    0.034363742119316115
+           array packing     0.10842431959999999     0.03169812767372563
+           block caching     0.11074702389999999     0.03237717622778925
+         parallelization     0.14659330210000002    0.042856927516092366
 
 
 
@@ -1654,7 +1654,7 @@ the computation for specific platforms.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  2.680 seconds)
+   **Total running time of the script:** ( 1 minutes  1.084 seconds)
 
 
 .. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/commit_hash b/docs/commit_hash
index 944482e15b..c8590f0509 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-78b53221f8dd8c1d2bbeff9d34803db33ca254dd
+44ed06ac9f019f9f06608504c3382d0905b6d5a2
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index aedfbbad50..b7e046ed8b 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  13.629 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  13.405 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 b1bb52252b..997de5d4b5 100644
--- a/docs/how_to/compile_models/from_keras.html
+++ b/docs/how_to/compile_models/from_keras.html
@@ -506,7 +506,7 @@ pip install -U tensorflow --user
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Relay top-1 id: 285, class name: Egyptian cat
 
 1/1 [==============================] - ETA: 0s
-1/1 [==============================] - 1s 958ms/step
+1/1 [==============================] - 1s 964ms/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 001decc494..3076dc5d23 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -440,7 +440,7 @@ to download the full example code</p>
 <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;x&quot;</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#tuple" title="builtins.tuple" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">x</span><span class="o">.</span><span class="n">shape</span></a><span class="p">)</span>
 </pre></div>
 </div>
-<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip6172288d-0a35-409b-9577-c9b5f252dbdd 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.zip6703bb06-6b2d-4042-9067-f67e09bca4e5 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 d2ace9f686..10c3f37b19 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -448,13 +448,14 @@ Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdo
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: &quot;https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip&quot; to /workspace/.oneflow/flowvision_cache/resnet18.zip
 
   0%|          | 0.00/41.5M [00:00&lt;?, ?B/s]
- 15%|#5        | 6.33M/41.5M [00:00&lt;00:00, 47.2MB/s]
- 26%|##6       | 10.8M/41.5M [00:00&lt;00:00, 38.8MB/s]
- 39%|###8      | 16.0M/41.5M [00:00&lt;00:00, 39.6MB/s]
- 58%|#####7    | 24.0M/41.5M [00:00&lt;00:00, 38.3MB/s]
- 77%|#######7  | 32.0M/41.5M [00:00&lt;00:00, 43.5MB/s]
- 87%|########7 | 36.2M/41.5M [00:00&lt;00:00, 43.4MB/s]
-100%|##########| 41.5M/41.5M [00:00&lt;00:00, 44.2MB/s]
+ 15%|#5        | 6.33M/41.5M [00:00&lt;00:00, 37.1MB/s]
+ 24%|##3       | 9.87M/41.5M [00:00&lt;00:01, 29.5MB/s]
+ 39%|###8      | 16.0M/41.5M [00:00&lt;00:00, 33.4MB/s]
+ 54%|#####3    | 22.3M/41.5M [00:00&lt;00:00, 42.2MB/s]
+ 73%|#######3  | 30.3M/41.5M [00:00&lt;00:00, 54.0MB/s]
+ 87%|########6 | 36.0M/41.5M [00:00&lt;00:00, 45.8MB/s]
+ 98%|#########8| 40.8M/41.5M [00:01&lt;00:00, 43.9MB/s]
+100%|##########| 41.5M/41.5M [00:01&lt;00:00, 42.9MB/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 32a63ad589..3c70333604 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -431,13 +431,14 @@ be unstable.</p>
 Downloading: &quot;https://download.pytorch.org/models/resnet18-f37072fd.pth&quot; to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
 
   0%|          | 0.00/44.7M [00:00&lt;?, ?B/s]
- 18%|#7        | 7.99M/44.7M [00:00&lt;00:00, 39.7MB/s]
- 36%|###5      | 16.0M/44.7M [00:00&lt;00:00, 46.9MB/s]
- 54%|#####3    | 24.1M/44.7M [00:00&lt;00:00, 57.7MB/s]
- 68%|######7   | 30.3M/44.7M [00:00&lt;00:00, 47.9MB/s]
- 79%|#######8  | 35.2M/44.7M [00:00&lt;00:00, 43.7MB/s]
- 90%|########9 | 40.0M/44.7M [00:00&lt;00:00, 39.0MB/s]
-100%|##########| 44.7M/44.7M [00:01&lt;00:00, 46.5MB/s]
+  6%|5         | 2.61M/44.7M [00:00&lt;00:01, 22.4MB/s]
+ 18%|#7        | 7.99M/44.7M [00:00&lt;00:01, 33.0MB/s]
+ 32%|###2      | 14.3M/44.7M [00:00&lt;00:01, 31.7MB/s]
+ 39%|###8      | 17.3M/44.7M [00:00&lt;00:00, 29.7MB/s]
+ 55%|#####4    | 24.5M/44.7M [00:00&lt;00:00, 41.9MB/s]
+ 72%|#######1  | 32.0M/44.7M [00:00&lt;00:00, 43.9MB/s]
+ 90%|########9 | 40.0M/44.7M [00:01&lt;00:00, 42.2MB/s]
+100%|##########| 44.7M/44.7M [00:01&lt;00:00, 42.3MB/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 a85fc16215..89f5e05ea6 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -645,7 +645,7 @@ 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  14.751 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  11.788 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 75f0c16580..f7ba3d0669 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>06:02.125</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:52.981</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 81%" />
@@ -348,44 +348,44 @@
 <col style="width: 8%" />
 </colgroup>
 <tbody>
-<tr class="row-odd"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:14.751</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
+<td><p>01:13.405</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>01:13.629</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
+<td><p>01:11.788</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>00:46.113</p></td>
+<td><p>00:46.658</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>00:35.536</p></td>
+<td><p>00:33.757</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>00:32.462</p></td>
+<td><p>00:30.473</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
-<td><p>00:28.438</p></td>
+<td><p>00:26.763</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
-<td><p>00:26.481</p></td>
+<td><p>00:25.790</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>00:24.117</p></td>
+<td><p>00:23.270</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>00:18.113</p></td>
+<td><p>00:18.636</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>00:02.485</p></td>
+<td><p>00:02.439</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 </tbody>
diff --git a/docs/how_to/deploy_models/deploy_model_on_android.html b/docs/how_to/deploy_models/deploy_model_on_android.html
index 423aa463e7..b7f68b86fa 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -661,7 +661,7 @@ to the remote android device.</p>
 Evaluate inference time cost...
 Execution time summary:
  mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)
-  16.0401      16.0527      16.2899      15.8806       0.1304
+  16.2805      16.3876      16.6878      15.6962       0.3367
 </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 eff7109d40..19a38bad0c 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -453,31 +453,32 @@ 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, 56.7MB/s]
-  9%|9         | 16.0M/170M [00:00&lt;00:02, 63.9MB/s]
- 14%|#4        | 24.0M/170M [00:00&lt;00:02, 53.8MB/s]
- 19%|#8        | 32.0M/170M [00:00&lt;00:02, 50.6MB/s]
- 24%|##3       | 40.0M/170M [00:00&lt;00:02, 55.8MB/s]
- 27%|##7       | 46.3M/170M [00:00&lt;00:02, 53.3MB/s]
- 32%|###2      | 54.5M/170M [00:00&lt;00:01, 61.5MB/s]
- 36%|###5      | 60.7M/170M [00:01&lt;00:01, 62.3MB/s]
- 39%|###9      | 66.9M/170M [00:01&lt;00:01, 62.1MB/s]
- 43%|####2     | 73.0M/170M [00:01&lt;00:01, 59.0MB/s]
- 46%|####6     | 78.7M/170M [00:01&lt;00:01, 59.2MB/s]
- 51%|#####     | 86.3M/170M [00:01&lt;00:01, 51.7MB/s]
- 54%|#####3    | 91.5M/170M [00:01&lt;00:01, 45.6MB/s]
- 57%|#####6    | 96.1M/170M [00:01&lt;00:01, 41.8MB/s]
- 60%|######    | 102M/170M [00:02&lt;00:01, 46.2MB/s]
- 64%|######4   | 109M/170M [00:02&lt;00:01, 52.0MB/s]
- 67%|######7   | 114M/170M [00:02&lt;00:01, 48.1MB/s]
- 71%|#######   | 120M/170M [00:02&lt;00:01, 49.8MB/s]
- 75%|#######5  | 128M/170M [00:02&lt;00:00, 56.6MB/s]
- 79%|#######9  | 134M/170M [00:02&lt;00:00, 58.0MB/s]
- 82%|########2 | 140M/170M [00:02&lt;00:00, 53.5MB/s]
- 86%|########5 | 146M/170M [00:02&lt;00:00, 55.1MB/s]
- 89%|########9 | 152M/170M [00:03&lt;00:00, 46.7MB/s]
- 94%|#########4| 160M/170M [00:03&lt;00:00, 49.9MB/s]
-100%|##########| 170M/170M [00:03&lt;00:00, 54.5MB/s]
+  5%|4         | 7.99M/170M [00:00&lt;00:02, 61.7MB/s]
+  8%|8         | 14.3M/170M [00:00&lt;00:04, 36.6MB/s]
+ 11%|#         | 18.2M/170M [00:00&lt;00:04, 37.0MB/s]
+ 13%|#3        | 22.3M/170M [00:00&lt;00:05, 29.5MB/s]
+ 15%|#4        | 25.4M/170M [00:00&lt;00:05, 29.7MB/s]
+ 21%|##        | 35.3M/170M [00:00&lt;00:02, 48.6MB/s]
+ 24%|##3       | 40.7M/170M [00:01&lt;00:02, 46.7MB/s]
+ 28%|##8       | 48.0M/170M [00:01&lt;00:02, 48.3MB/s]
+ 33%|###2      | 56.0M/170M [00:01&lt;00:02, 52.5MB/s]
+ 38%|###7      | 64.0M/170M [00:01&lt;00:01, 58.0MB/s]
+ 42%|####2     | 72.0M/170M [00:01&lt;00:01, 53.5MB/s]
+ 47%|####7     | 80.0M/170M [00:01&lt;00:01, 53.3MB/s]
+ 51%|#####     | 86.3M/170M [00:01&lt;00:01, 56.0MB/s]
+ 54%|#####4    | 91.9M/170M [00:01&lt;00:01, 56.0MB/s]
+ 58%|#####8    | 98.6M/170M [00:02&lt;00:01, 59.6MB/s]
+ 62%|######1   | 104M/170M [00:02&lt;00:01, 54.0MB/s]
+ 68%|######7   | 115M/170M [00:02&lt;00:00, 68.1MB/s]
+ 72%|#######1  | 122M/170M [00:02&lt;00:00, 66.7MB/s]
+ 76%|#######5  | 128M/170M [00:02&lt;00:00, 64.8MB/s]
+ 80%|########  | 136M/170M [00:02&lt;00:00, 56.4MB/s]
+ 83%|########3 | 142M/170M [00:02&lt;00:00, 51.1MB/s]
+ 87%|########7 | 148M/170M [00:02&lt;00:00, 54.5MB/s]
+ 90%|######### | 153M/170M [00:03&lt;00:00, 42.6MB/s]
+ 94%|#########4| 160M/170M [00:03&lt;00:00, 45.1MB/s]
+ 99%|#########8| 168M/170M [00:03&lt;00:00, 53.5MB/s]
+100%|##########| 170M/170M [00:03&lt;00:00, 51.6MB/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=& [...]
@@ -575,7 +576,7 @@ 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  21.658 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  16.971 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 d29b20b59f..8e4a83a16e 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -497,8 +497,9 @@ 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, 59.0MB/s]
-100%|##########| 13.6M/13.6M [00:00&lt;00:00, 61.4MB/s]
+ 47%|####6     | 6.30M/13.6M [00:00&lt;00:00, 63.1MB/s]
+ 91%|######### | 12.3M/13.6M [00:00&lt;00:00, 44.4MB/s]
+100%|##########| 13.6M/13.6M [00:00&lt;00:00, 50.0MB/s]
 </pre></div>
 </div>
 </div>
@@ -589,7 +590,7 @@ 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)
-  90.5403      90.5017      94.8389      90.1184       0.4960
+  90.4050      90.3277      95.0359      90.0595       0.4947
 </pre></div>
 </div>
 <div class="admonition note">
@@ -628,7 +629,7 @@ This includes support for the VNNI 8 bit dot product instruction (CascadeLake or
 <div class="section" id="deploy-a-quantized-tflite-model">
 <h2>Deploy a quantized TFLite Model<a class="headerlink" href="#deploy-a-quantized-tflite-model" title="Permalink to this headline">¶</a></h2>
 <p>TODO</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  10.807 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  6.767 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 e75177c4c0..2bcf0c8f62 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -582,7 +582,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
  mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)
-  119.4717     119.3346     124.6189     118.5417      0.7517
+  120.9329     120.8553     125.1488     120.2441      0.5669
 </pre></div>
 </div>
 <div class="admonition note">
@@ -610,7 +610,7 @@ 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  30.840 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes  31.481 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 719e8f7090..f390391acf 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -520,7 +520,7 @@ 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  42.918 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  39.807 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 6f44d235fe..2bc958574b 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -462,24 +462,22 @@ to your device.</p>
 Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
 
   0%|          | 0/132723 [00:00&lt;?, ?KB/s]
-  5%|5         | 6912/132723 [00:00&lt;00:01, 69106.06KB/s]
- 11%|#1        | 15152/132723 [00:00&lt;00:01, 68122.83KB/s]
- 17%|#6        | 21972/132723 [00:00&lt;00:02, 39543.87KB/s]
- 23%|##2       | 30354/132723 [00:00&lt;00:02, 51109.35KB/s]
- 28%|##8       | 37497/132723 [00:00&lt;00:01, 56165.70KB/s]
- 34%|###3      | 44486/132723 [00:00&lt;00:01, 59980.29KB/s]
- 39%|###8      | 51150/132723 [00:00&lt;00:01, 54000.24KB/s]
- 45%|####4     | 59588/132723 [00:01&lt;00:01, 61946.16KB/s]
- 50%|####9     | 66313/132723 [00:01&lt;00:01, 61297.42KB/s]
- 56%|#####6    | 74717/132723 [00:01&lt;00:00, 67508.51KB/s]
- 62%|######1   | 81798/132723 [00:01&lt;00:00, 62225.58KB/s]
- 67%|######6   | 88311/132723 [00:01&lt;00:01, 43222.78KB/s]
- 73%|#######2  | 96688/132723 [00:01&lt;00:00, 51636.36KB/s]
- 78%|#######7  | 102894/132723 [00:01&lt;00:00, 53736.48KB/s]
- 84%|########3 | 111335/132723 [00:01&lt;00:00, 61258.35KB/s]
- 89%|########9 | 118185/132723 [00:02&lt;00:00, 50980.55KB/s]
- 95%|#########5| 126549/132723 [00:02&lt;00:00, 58502.28KB/s]
-100%|##########| 132723/132723 [00:02&lt;00:00, 56851.09KB/s]
+  6%|5         | 7359/132723 [00:00&lt;00:01, 73578.32KB/s]
+ 12%|#2        | 16072/132723 [00:00&lt;00:01, 81546.45KB/s]
+ 18%|#8        | 24227/132723 [00:00&lt;00:01, 62005.86KB/s]
+ 25%|##4       | 32757/132723 [00:00&lt;00:02, 43299.33KB/s]
+ 31%|###1      | 41408/132723 [00:00&lt;00:01, 53118.25KB/s]
+ 38%|###7      | 50040/132723 [00:00&lt;00:01, 61252.25KB/s]
+ 44%|####4     | 58670/132723 [00:00&lt;00:01, 67745.91KB/s]
+ 51%|#####     | 67351/132723 [00:01&lt;00:00, 72896.78KB/s]
+ 57%|#####7    | 75784/132723 [00:01&lt;00:00, 76080.18KB/s]
+ 63%|######3   | 84228/132723 [00:01&lt;00:00, 78457.65KB/s]
+ 70%|######9   | 92783/132723 [00:01&lt;00:00, 80506.54KB/s]
+ 76%|#######6  | 101108/132723 [00:01&lt;00:00, 70659.05KB/s]
+ 83%|########2 | 109815/132723 [00:01&lt;00:00, 75025.98KB/s]
+ 89%|########8 | 118048/132723 [00:01&lt;00:00, 77036.58KB/s]
+ 95%|#########5| 126742/132723 [00:01&lt;00:00, 79831.45KB/s]
+100%|##########| 132723/132723 [00:01&lt;00:00, 69886.02KB/s]
 </pre></div>
 </div>
 <p>Create TVM runtime and do inference
@@ -518,7 +516,7 @@ 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  3.754 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  2.439 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 d23124728d..c7dec099dd 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>13:22.160</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>13:04.439</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 86%" />
@@ -349,35 +349,35 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>03:21.658</p></td>
+<td><p>03:16.971</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>03:03.754</p></td>
+<td><p>03:02.439</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>02:30.840</p></td>
+<td><p>02:31.481</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>01:42.918</p></td>
+<td><p>01:39.807</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized.html#sphx-glr-how-to-deploy-models-deploy-prequantized-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized.py</span></code>)</p></td>
-<td><p>01:10.807</p></td>
+<td><p>01:06.767</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:38.804</p></td>
+<td><p>00:36.121</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_nano.html#sphx-glr-how-to-deploy-models-deploy-model-on-nano-py"><span class="std std-ref">Deploy the Pretrained Model on Jetson Nano</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_nano.py</span></code>)</p></td>
-<td><p>00:26.989</p></td>
+<td><p>00:25.702</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:26.383</p></td>
+<td><p>00:25.146</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index a210593110..de9eae7ee1 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -621,7 +621,7 @@ 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.zipccbf2386-7e57-408a-8b03-16a9002a6478 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.zipb5ec6e0e-1a2e-4ead-b5c9-a1715a34eb53 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 f431be00d9..f076ce89ae 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>00:48.149</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:48.729</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>00:44.665</p></td>
+<td><p>00:45.240</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>00:02.437</p></td>
+<td><p>00:02.441</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>00:01.039</p></td>
+<td><p>00:01.040</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 f0042bca92..a7c187a4d4 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -525,10 +525,10 @@ 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: 7176us [7176us] (46.30%; 46.30%)
-FoldScaleAxis: 8322us [6us] (53.70%; 53.70%)
-        FoldConstant: 8315us [1690us] (53.66%; 99.92%)
-                InferType: 6626us [6626us] (42.75%; 79.68%)
+InferType: 7091us [7091us] (45.25%; 45.25%)
+FoldScaleAxis: 8579us [7us] (54.75%; 54.75%)
+        FoldConstant: 8572us [1775us] (54.70%; 99.92%)
+                InferType: 6796us [6796us] (43.37%; 79.29%)
 </pre></div>
 </div>
 </div>
@@ -550,10 +550,10 @@ 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: 6651us [6651us] (45.01%; 45.01%)
-FoldScaleAxis: 8127us [5us] (54.99%; 54.99%)
-        FoldConstant: 8122us [1678us] (54.96%; 99.94%)
-                InferType: 6444us [6444us] (43.61%; 79.34%)
+InferType: 6623us [6623us] (44.82%; 44.82%)
+FoldScaleAxis: 8153us [5us] (55.18%; 55.18%)
+        FoldConstant: 8148us [1692us] (55.14%; 99.94%)
+                InferType: 6456us [6456us] (43.69%; 79.24%)
 </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 e8b02229ae..6e6394afb1 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -577,7 +577,7 @@ 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: 41.190143 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 34.213375 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 cac478e018..772dbde193 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -914,7 +914,7 @@ 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: 13.362189 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 13.353340 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 a8d43ae6ad..c6a071a04d 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -474,8 +474,8 @@ 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: 0.018437
-Baseline: 3.542359
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019583
+Baseline: 3.429270
 </pre></div>
 </div>
 <p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -534,7 +534,7 @@ 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: 0.305990
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.308873
 </pre></div>
 </div>
 <p>Here is the generated IR after blocking.</p>
@@ -600,7 +600,7 @@ 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: 0.335689
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.331130
 </pre></div>
 </div>
 <p>Here is the generated IR after vectorization.</p>
@@ -660,7 +660,7 @@ 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: 0.116123
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.116499
 </pre></div>
 </div>
 <p>Here is the generated IR after loop permutation.</p>
@@ -742,7 +742,7 @@ 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: 0.110101
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109366
 </pre></div>
 </div>
 <p>Here is the generated IR after array packing.</p>
@@ -827,7 +827,7 @@ 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: 0.111848
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111082
 </pre></div>
 </div>
 <p>Here is the generated IR after blocking.</p>
@@ -916,7 +916,7 @@ write to C when all the block results are ready.</p>
 <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;Opt6: </span><span class="si">%f</span><span class="s2">&quot;</span> <span class="o">%</span> <span class="n">opt6_time</span><span class="p">)</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.147245
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.147840
 </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 a08aa0ef96..bf2257e4d6 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>00:35.417</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:35.433</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>00:32.836</p></td>
+<td><p>00:32.596</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>00:01.521</p></td>
+<td><p>00:01.698</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>00:01.061</p></td>
+<td><p>00:01.138</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 d85ef7c18b..d1caedd9db 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>09:43.171</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>09:22.962</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>06:07.710</p></td>
+<td><p>05:52.239</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="tune_network_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-x86-py"><span class="std std-ref">Auto-scheduling a Neural Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_x86.py</span></code>)</p></td>
-<td><p>01:34.567</p></td>
+<td><p>01:34.879</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>01:04.692</p></td>
+<td><p>01:04.373</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="tune_sparse_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-sparse-x86-py"><span class="std std-ref">Auto-scheduling Sparse Matrix Multiplication on CPU with Custom Sketch Rule</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_sparse_x86.py</span></code>)</p></td>
-<td><p>00:31.234</p></td>
+<td><p>00:27.840</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></td>
-<td><p>00:12.963</p></td>
+<td><p>00:12.218</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>00:12.004</p></td>
+<td><p>00:11.414</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 784debe5c7..4657ab6747 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
@@ -503,483 +503,191 @@ cooperative fetching, unrolling and operator fusion.</p>
              bias: Buffer(bias_2: Pointer(float32), float32, [1, 512, 1, 1], []),
              compute: Buffer(compute_2: Pointer(float32), float32, [1, 512, 7, 7], [])}
   buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute} {
-  attr [IterVar(blockIdx.x: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;blockIdx.x&quot;)] &quot;thread_extent&quot; = 28;
-  allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
-  allocate(pad_temp.shared: Pointer(shared float32), float32, [72]), storage_scope = shared;
-  allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
-  attr [IterVar(threadIdx.x: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64 {
-    conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope=&quot;local&quot;, align=32)[0] = 0f32
+  attr [IterVar(blockIdx.x: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;blockIdx.x&quot;)] &quot;thread_extent&quot; = 128;
+  allocate(conv2d_nchw: Pointer(local float32), float32, [4]), storage_scope = local;
+  allocate(pad_temp.shared: Pointer(shared float32), float32, [324]), storage_scope = shared;
+  allocate(kernel.shared: Pointer(shared float32), float32, [144]), storage_scope = shared;
+  attr [IterVar(threadIdx.x: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 49 {
+    conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope=&quot;local&quot;, align=16)[0] = 0f32
     conv2d_nchw_1[1] = 0f32
     conv2d_nchw_1[2] = 0f32
     conv2d_nchw_1[3] = 0f32
-    conv2d_nchw_1[4] = 0f32
-    conv2d_nchw_1[5] = 0f32
-    conv2d_nchw_1[6] = 0f32
-    conv2d_nchw_1[7] = 0f32
-    conv2d_nchw_1[8] = 0f32
-    conv2d_nchw_1[9] = 0f32
-    conv2d_nchw_1[10] = 0f32
-    conv2d_nchw_1[11] = 0f32
-    conv2d_nchw_1[12] = 0f32
-    conv2d_nchw_1[13] = 0f32
-    for (rc.outer.outer: int32, 0, 64) {
-      for (ry.outer.outer: int32, 0, 3) {
-        let cse_var_2: int32 = (rc.outer.outer*72)
-        let cse_var_1: int32 = (ry.outer.outer*3)
-         {
-          attr [IterVar(threadIdx.x_1: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64 {
-            if @tir.likely((threadIdx.x_1 &lt; 18), dtype=bool) {
-              pad_temp.shared_1: Buffer(pad_temp.shared, float32, [72], [], scope=&quot;shared&quot;)[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 &lt;= (ry.outer.outer + floormod(blockIdx.x, 7))) &amp;&amp; ((ry.outer.outer + floormod(blockIdx.x, 7)) &lt; 8)) &amp;&amp; (1 &lt;= floormod((threadIdx.x_1*4), 9))) &amp;&amp; (floormod((threadIdx.x_1*4), 9) &lt; 8)), data_3: Buffer(data_2, float32, [25088], [])[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*4), 9)*49)) + (ry.outer.out [...]
-            }
-            if @tir.likely((threadIdx.x_1 &lt; 18), dtype=bool) {
-              pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 &lt;= (ry.outer.outer + floormod(blockIdx.x, 7))) &amp;&amp; ((ry.outer.outer + floormod(blockIdx.x, 7)) &lt; 8)) &amp;&amp; (1 &lt;= floormod(((threadIdx.x_1*4) + 1), 9))) &amp;&amp; (floormod(((threadIdx.x_1*4) + 1), 9) &lt; 8)), data_3[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 1), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], [...]
-            }
-            if @tir.likely((threadIdx.x_1 &lt; 18), dtype=bool) {
-              pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 &lt;= (ry.outer.outer + floormod(blockIdx.x, 7))) &amp;&amp; ((ry.outer.outer + floormod(blockIdx.x, 7)) &lt; 8)) &amp;&amp; (1 &lt;= floormod(((threadIdx.x_1*4) + 2), 9))) &amp;&amp; (floormod(((threadIdx.x_1*4) + 2), 9) &lt; 8)), data_3[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 2), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], [...]
-            }
-            if @tir.likely((threadIdx.x_1 &lt; 18), dtype=bool) {
-              pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 &lt;= (ry.outer.outer + floormod(blockIdx.x, 7))) &amp;&amp; ((ry.outer.outer + floormod(blockIdx.x, 7)) &lt; 8)) &amp;&amp; (1 &lt;= floormod(((threadIdx.x_1*4) + 3), 9))) &amp;&amp; (floormod(((threadIdx.x_1*4) + 3), 9) &lt; 8)), data_3[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 3), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], [...]
-            }
-          }
-          attr [IterVar(threadIdx.x_2: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope=&quot;shared&quot;)[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 64)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 64), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 128)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 128), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 192)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 256)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 256), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 320)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 320), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 384)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 448)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 448), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 512)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 512), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 576)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 640)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 640), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 704)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 704), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 768)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 147456)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 832)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 832), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 896)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 896), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 960)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 184320)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1024), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1088), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 221184)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1216), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1280), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1408), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1472), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 294912)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1600), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1664), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 331776)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1792), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1856), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 368640)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1984), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2048), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 405504)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2176), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2240), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 442368)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2368), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2432), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 479232)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2560), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2624), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 516096)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2752), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2816), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 552960)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2944), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3008), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*48)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*48)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*48)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*48)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*48)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*48)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*48)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+    for (rc.outer.outer: int32, 0, 128) {
+      let cse_var_2: int32 = (rc.outer.outer*196)
+      let cse_var_1: int32 = (rc.outer.outer*36)
+       {
+        attr [IterVar(threadIdx.x_1: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 49;
+        pad_temp.shared_1: Buffer(pad_temp.shared, float32, [324], [], scope=&quot;shared&quot;)[threadIdx.x_1] = @tir.if_then_else((((9 &lt;= threadIdx.x_1) &amp;&amp; (1 &lt;= floormod(threadIdx.x_1, 9))) &amp;&amp; (floormod(threadIdx.x_1, 9) &lt; 8)), data_3: Buffer(data_2, float32, [25088], [])[(((cse_var_2 + (floordiv(threadIdx.x_1, 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+        attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 49;
+        pad_temp.shared_1[(threadIdx.x_1 + 49)] = @tir.if_then_else(((((9 &lt;= floormod((threadIdx.x_1 + 49), 81)) &amp;&amp; (floormod((threadIdx.x_1 + 49), 81) &lt; 72)) &amp;&amp; (1 &lt;= floormod((threadIdx.x_1 + 4), 9))) &amp;&amp; (floormod((threadIdx.x_1 + 4), 9) &lt; 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 49), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 49), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+        attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 49;
+        pad_temp.shared_1[(threadIdx.x_1 + 98)] = @tir.if_then_else(((1 &lt;= floormod((threadIdx.x_1 + 8), 9)) &amp;&amp; (floormod((threadIdx.x_1 + 8), 9) &lt; 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 98), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 17), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+        attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 49;
+        pad_temp.shared_1[(threadIdx.x_1 + 147)] = @tir.if_then_else(((((9 &lt;= floormod((threadIdx.x_1 + 66), 81)) &amp;&amp; (floormod((threadIdx.x_1 + 66), 81) &lt; 72)) &amp;&amp; (1 &lt;= floormod((threadIdx.x_1 + 3), 9))) &amp;&amp; (floormod((threadIdx.x_1 + 3), 9) &lt; 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 147), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 66), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+        attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 49;
+        pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((((9 &lt;= floormod((threadIdx.x_1 + 34), 81)) &amp;&amp; (floormod((threadIdx.x_1 + 34), 81) &lt; 72)) &amp;&amp; (1 &lt;= floormod((threadIdx.x_1 + 7), 9))) &amp;&amp; (floormod((threadIdx.x_1 + 7), 9) &lt; 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 196), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 34), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+        attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 49;
+        pad_temp.shared_1[(threadIdx.x_1 + 245)] = @tir.if_then_else((((9 &lt;= floormod((threadIdx.x_1 + 2), 81)) &amp;&amp; (1 &lt;= floormod((threadIdx.x_1 + 2), 9))) &amp;&amp; (floormod((threadIdx.x_1 + 2), 9) &lt; 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 245), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 2), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+        attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 49;
+        if @tir.likely((threadIdx.x_1 &lt; 30), dtype=bool) {
+          pad_temp.shared_1[(threadIdx.x_1 + 294)] = @tir.if_then_else((((threadIdx.x_1 &lt; 21) &amp;&amp; (1 &lt;= floormod((threadIdx.x_1 + 6), 9))) &amp;&amp; (floormod((threadIdx.x_1 + 6), 9) &lt; 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 294), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 51), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
         }
+        attr [IterVar(threadIdx.x_2: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 49;
+        kernel.shared_1: Buffer(kernel.shared, float32, [144], [], scope=&quot;shared&quot;)[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 36)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 36))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 49;
+        kernel.shared_1[(threadIdx.x_2 + 49)] = kernel_3[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 49), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 13), 36), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 4), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 49;
+        if @tir.likely((threadIdx.x_2 &lt; 46), dtype=bool) {
+          kernel.shared_1[(threadIdx.x_2 + 98)] = kernel_3[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 98), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 26), 36), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 8), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+        }
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[0]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[9]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[36]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[45]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[72]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[81]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[108]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[117]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[1]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[10]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[37]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[46]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[73]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[82]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[109]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[118]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[2]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[11]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[38]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[47]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[74]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[83]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[110]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[119]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[3]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[12]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[39]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[48]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[75]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[84]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[111]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[120]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[4]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[13]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[40]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[49]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[76]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[85]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[112]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[121]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[5]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[14]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[41]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[50]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[77]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[86]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[113]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[122]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[6]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[15]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[42]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[51]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[78]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[87]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[114]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[123]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[7]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[16]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[43]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[52]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[79]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[88]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[115]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[124]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[8]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[17]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[44]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[53]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[80]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[89]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[116]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[125]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[18]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[27]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[54]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[63]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[90]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[99]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[126]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[135]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[19]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[28]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[55]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[64]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[91]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[100]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[127]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[136]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[20]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[29]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[56]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[65]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[92]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[101]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[128]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[137]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[21]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[30]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[57]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[66]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[93]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[102]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[129]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[138]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[22]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[31]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[58]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[67]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[94]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[103]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[130]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[139]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[23]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[32]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[59]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[68]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[95]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[104]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[131]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[140]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[24]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[33]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[60]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[69]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[96]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[105]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[132]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[141]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[25]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[34]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[61]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[70]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[97]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[106]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[133]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[142]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[26]))
+        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[35]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[62]))
+        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[71]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[98]))
+        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[107]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[134]))
+        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[143]))
       }
     }
-    for (i1.inner: int32, 0, 2) {
-      for (i3.inner: int32, 0, 7) {
-        compute_3: Buffer(compute_2, float32, [25088], [])[(((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias_3: Buffer(bias_2, float32, [512], [])[(((floordiv(blockIdx.x, 7)*128) + (threadIdx.x*2)) + i1.inner)]), 0f32)
-      }
+    for (i1.inner: int32, 0, 4) {
+      compute_3: Buffer(compute_2, float32, [25088], [])[(((blockIdx.x*196) + (i1.inner*49)) + threadIdx.x)] = max((conv2d_nchw_1[i1.inner] + bias_3: Buffer(bias_2, float32, [512], [])[((blockIdx.x*4) + i1.inner)]), 0f32)
     }
   }
 }
@@ -1016,7 +724,7 @@ cooperative fetching, unrolling and operator fusion.</p>
 <span class="p">)</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.349 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.259 ms
 </pre></div>
 </div>
 </div>
@@ -1046,35 +754,35 @@ conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o
 conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
 conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
 conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
-conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
+conv2d_nchw_ff_o_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=1)
 conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
 conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
 conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
-conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
+conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
 conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
 conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
-conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
-conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
+conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
+conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
 conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
 conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
 conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
-conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
+conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
 conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
 conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
 s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
 compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
 compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
 compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
-compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
+compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=4)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=1)
 compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
 compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
-compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
 compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
-compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
-compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
+compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
+compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
 compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
 s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
 s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -1094,12 +802,12 @@ s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread
 kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
 kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
 s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=49)
 s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis(&quot;threadIdx.x&quot;))
 pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=4)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
 s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=49)
 s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis(&quot;threadIdx.x&quot;))
 s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, &quot;auto_unroll_max_step&quot;, 512)
 s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, &quot;unroll_explicit&quot;, True)
@@ -1119,430 +827,178 @@ CUDA source code:
   #define int64_t long long
   #define uint64_t unsigned long long
 #endif
-extern &quot;C&quot; __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
-  float conv2d_nchw[14];
-  __shared__ float pad_temp_shared[72];
-  __shared__ float kernel_shared[3072];
+extern &quot;C&quot; __global__ void __launch_bounds__(49) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+  float conv2d_nchw[4];
+  __shared__ float pad_temp_shared[324];
+  __shared__ float kernel_shared[144];
   conv2d_nchw[0] = 0.000000e+00f;
   conv2d_nchw[1] = 0.000000e+00f;
   conv2d_nchw[2] = 0.000000e+00f;
   conv2d_nchw[3] = 0.000000e+00f;
-  conv2d_nchw[4] = 0.000000e+00f;
-  conv2d_nchw[5] = 0.000000e+00f;
-  conv2d_nchw[6] = 0.000000e+00f;
-  conv2d_nchw[7] = 0.000000e+00f;
-  conv2d_nchw[8] = 0.000000e+00f;
-  conv2d_nchw[9] = 0.000000e+00f;
-  conv2d_nchw[10] = 0.000000e+00f;
-  conv2d_nchw[11] = 0.000000e+00f;
-  conv2d_nchw[12] = 0.000000e+00f;
-  conv2d_nchw[13] = 0.000000e+00f;
-  for (int rc_outer_outer = 0; rc_outer_outer &lt; 64; ++rc_outer_outer) {
-    for (int ry_outer_outer = 0; ry_outer_outer &lt; 3; ++ry_outer_outer) {
-      __syncthreads();
-      if (((int)threadIdx.x) &lt; 18) {
-        pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 &lt;= (ry_outer_outer + (((int)blockIdx.x) % 7))) &amp;&amp; ((ry_outer_outer + (((int)blockIdx.x) % 7)) &lt; 8)) &amp;&amp; (1 &lt;= ((((int)threadIdx.x) * 4) % 9))) &amp;&amp; (((((int)threadIdx.x) * 4) % 9) &lt; 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
-      }
-      if (((int)threadIdx.x) &lt; 18) {
-        pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 &lt;= (ry_outer_outer + (((int)blockIdx.x) % 7))) &amp;&amp; ((ry_outer_outer + (((int)blockIdx.x) % 7)) &lt; 8)) &amp;&amp; (1 &lt;= (((((int)threadIdx.x) * 4) + 1) % 9))) &amp;&amp; ((((((int)threadIdx.x) * 4) + 1) % 9) &lt; 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
-      }
-      if (((int)threadIdx.x) &lt; 18) {
-        pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 &lt;= (ry_outer_outer + (((int)blockIdx.x) % 7))) &amp;&amp; ((ry_outer_outer + (((int)blockIdx.x) % 7)) &lt; 8)) &amp;&amp; (1 &lt;= (((((int)threadIdx.x) * 4) + 2) % 9))) &amp;&amp; ((((((int)threadIdx.x) * 4) + 2) % 9) &lt; 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
-      }
-      if (((int)threadIdx.x) &lt; 18) {
-        pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 &lt;= (ry_outer_outer + (((int)blockIdx.x) % 7))) &amp;&amp; ((ry_outer_outer + (((int)blockIdx.x) % 7)) &lt; 8)) &amp;&amp; (1 &lt;= (((((int)threadIdx.x) * 4) + 3) % 9))) &amp;&amp; ((((((int)threadIdx.x) * 4) + 3) % 9) &lt; 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
-      }
-      kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
-      kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
-      kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
-      kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
-      kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
-      kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
-      kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
-      kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
-      kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
-      kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
-      kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
-      kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
-      kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
-      kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
-      kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
-      kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      __syncthreads();
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 48)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 48)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 48)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 48)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 48)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 48)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 48)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+  for (int rc_outer_outer = 0; rc_outer_outer &lt; 128; ++rc_outer_outer) {
+    __syncthreads();
+    pad_temp_shared[((int)threadIdx.x)] = ((((9 &lt;= ((int)threadIdx.x)) &amp;&amp; (1 &lt;= (((int)threadIdx.x) % 9))) &amp;&amp; ((((int)threadIdx.x) % 9) &lt; 8)) ? data[((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+    pad_temp_shared[(((int)threadIdx.x) + 49)] = (((((9 &lt;= ((((int)threadIdx.x) + 49) % 81)) &amp;&amp; (((((int)threadIdx.x) + 49) % 81) &lt; 72)) &amp;&amp; (1 &lt;= ((((int)threadIdx.x) + 4) % 9))) &amp;&amp; (((((int)threadIdx.x) + 4) % 9) &lt; 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 49) / 81) * 49)) + ((((((int)threadIdx.x) + 49) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 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) / 81) * 49)) + (((((int)threadIdx.x) + 17) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+    pad_temp_shared[(((int)threadIdx.x) + 147)] = (((((9 &lt;= ((((int)threadIdx.x) + 66) % 81)) &amp;&amp; (((((int)threadIdx.x) + 66) % 81) &lt; 72)) &amp;&amp; (1 &lt;= ((((int)threadIdx.x) + 3) % 9))) &amp;&amp; (((((int)threadIdx.x) + 3) % 9) &lt; 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 147) / 81) * 49)) + ((((((int)threadIdx.x) + 66) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+    pad_temp_shared[(((int)threadIdx.x) + 196)] = (((((9 &lt;= ((((int)threadIdx.x) + 34) % 81)) &amp;&amp; (((((int)threadIdx.x) + 34) % 81) &lt; 72)) &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) / 81) * 49)) + ((((((int)threadIdx.x) + 34) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+    pad_temp_shared[(((int)threadIdx.x) + 245)] = ((((7 &lt;= ((int)threadIdx.x)) &amp;&amp; (1 &lt;= ((((int)threadIdx.x) + 2) % 9))) &amp;&amp; (((((int)threadIdx.x) + 2) % 9) &lt; 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 245) / 81) * 49)) + (((((int)threadIdx.x) + 2) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+    if (((int)threadIdx.x) &lt; 30) {
+      pad_temp_shared[(((int)threadIdx.x) + 294)] = ((((((int)threadIdx.x) &lt; 21) &amp;&amp; (1 &lt;= ((((int)threadIdx.x) + 6) % 9))) &amp;&amp; (((((int)threadIdx.x) + 6) % 9) &lt; 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 294) / 81) * 49)) + (((((int)threadIdx.x) + 51) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
     }
-  }
-  for (int i1_inner = 0; i1_inner &lt; 2; ++i1_inner) {
-    for (int i3_inner = 0; i3_inner &lt; 7; ++i3_inner) {
-      compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
+    kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) % 36))];
+    kernel_shared[(((int)threadIdx.x) + 49)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 49) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 13) % 36) / 9) * 9)) + ((((((int)threadIdx.x) + 4) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+    if (((int)threadIdx.x) &lt; 46) {
+      kernel_shared[(((int)threadIdx.x) + 98)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 98) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 26) % 36) / 9) * 9)) + ((((((int)threadIdx.x) + 8) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
     }
+    __syncthreads();
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[0]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[9]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[36]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[45]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[72]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[81]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[108]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[117]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[1]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[10]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[37]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[46]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[73]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[82]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[109]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[118]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[2]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[11]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[38]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[47]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[74]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[83]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[110]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[119]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[3]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[12]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[39]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[48]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[75]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[84]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[111]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[120]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[4]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[13]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[40]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[49]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[76]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[85]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[112]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[121]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[5]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[14]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[41]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[50]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[77]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[86]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[113]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[122]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[6]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[15]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[42]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[51]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[78]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[87]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[114]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[123]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[7]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[16]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[43]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[52]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[79]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[88]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[115]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[124]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[8]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[17]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[44]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[53]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[80]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[89]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[116]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[125]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[18]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[27]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[54]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[63]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[90]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[99]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[126]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[135]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[19]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[28]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[55]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[64]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[91]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[100]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[127]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[136]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[20]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[29]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[56]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[65]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[92]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[101]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[128]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[137]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[21]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[30]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[57]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[66]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[93]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[102]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[129]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[138]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[22]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[31]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[58]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[67]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[94]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[103]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[130]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[139]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[23]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[32]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[59]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[68]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[95]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[104]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[131]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[140]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[24]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[33]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[60]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[69]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[96]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[105]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[132]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[141]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[25]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[34]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[61]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[70]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[97]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[106]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[133]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[142]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[26]));
+    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[35]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[62]));
+    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[71]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[98]));
+    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[107]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[134]));
+    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[143]));
+  }
+  for (int i1_inner = 0; i1_inner &lt; 4; ++i1_inner) {
+    compute[(((((int)blockIdx.x) * 196) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 4) + i1_inner)]), 0.000000e+00f);
   }
 }
 </pre></div>
@@ -1577,9 +1033,10 @@ In the example below we resume the status and do more 5 trials.</p>
 /venv/apache-tvm-py3.7/lib/python3.7/site-packages/xgboost/training.py:17: UserWarning: Old style callback is deprecated.  See: https://xgboost.readthedocs.io/en/latest/python/callbacks.html
   warnings.warn(f&#39;Old style callback is deprecated.  See: {link}&#39;, UserWarning)
 Get devices for measurement successfully!
+.T
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes  7.710 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes  52.239 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 1e7eeb41cd..da62ad4398 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -915,7 +915,7 @@ 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)
-   8.1987       8.1995       8.2098       8.1868       0.0094
+   8.2691       8.2682       8.2786       8.2605       0.0074
 </pre></div>
 </div>
 </div>
@@ -937,7 +937,7 @@ 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  4.692 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  4.373 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 b98474935d..afeacb21a0 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -934,7 +934,7 @@ 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)
-  752.0948     752.5188     753.8207     749.9449      1.6104
+  765.1622     765.7585     766.9518     762.7763      1.7560
 </pre></div>
 </div>
 </div>
@@ -956,7 +956,7 @@ to learn how to use the RPC Tracker and RPC Server.
 To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
 with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
 </ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  34.567 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  34.879 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 f4c1cef722..7dd844db9b 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -632,28 +632,31 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
              placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [128, 512], []),
              compute: Buffer(compute_2: Pointer(float32), float32, [128, 512], [])}
   buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute} {
-  for (i0.outer.i1.outer.fused: int32, 0, 32) &quot;parallel&quot; {
-    allocate(compute_3: Pointer(global float32), float32, [2048]), storage_scope = global {
-      for (i.outer.inner: int32, 0, 2) {
-        for (i.inner.init: int32, 0, 64) {
+  for (i0.outer.i1.outer.fused: int32, 0, 128) &quot;parallel&quot; {
+    allocate(compute_3: Pointer(global float32), float32, [512]), storage_scope = global {
+      for (i.outer.inner: int32, 0, 8) {
+        for (i.inner.init: int32, 0, 4) {
           for (j.init: int32, 0, 16) {
-            compute_4: Buffer(compute_3, float32, [2048], [])[(((i.outer.inner*1024) + (i.inner.init*16)) + j.init)] = 0f32
+            compute_4: Buffer(compute_3, float32, [512], [])[(((i.outer.inner*64) + (i.inner.init*16)) + j.init)] = 0f32
           }
         }
-        for (elem_idx: int32, 0, (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])) {
-          for (i.inner: int32, 0, 64) {
+        for (elem_idx: int32, 0, let cse_var_1: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_1 + 1)] - placeholder_15[cse_var_1])) {
+          for (i.inner: int32, 0, 4) {
             for (j: int32, 0, 16) {
-              if @tir.likely((elem_idx &lt; (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
-                let cse_var_1: int32 = (((i.outer.inner*1024) + (i.inner*16)) + j)
-                compute_4[cse_var_1] = (compute_4[cse_var_1] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + j)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+              let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32)
+              if @tir.likely((elem_idx &lt; (placeholder_15[(cse_var_2 + 1)] - placeholder_15[cse_var_2])), dtype=bool) {
+                let cse_var_3: int32 = (((i.outer.inner*64) + (i.inner*16)) + j)
+                compute_4[cse_var_3] = (compute_4[cse_var_3] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[(((placeholder_15[cse_var_2]*16) + (elem_idx*16)) + j)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_2] + elem_idx)])], 0f32)))
               }
             }
           }
         }
       }
-      for (i0.inner: int32, 0, 128) {
-        let cse_var_2: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*16))
-        compute_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_2, 1, 16)] = max((compute_4[ramp((i0.inner*16), 1, 16)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_2, 1, 16)]), broadcast(0f32, 16))
+      for (i0.inner: int32, 0, 32) {
+        for (i1.inner: int32, 0, 16) {
+          let cse_var_4: int32 = ((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16)) + i1.inner)
+          compute_5: Buffer(compute_2, float32, [65536], [])[cse_var_4] = max((compute_4[((i0.inner*16) + i1.inner)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[cse_var_4]), 0f32)
+        }
       }
     }
   }
@@ -691,7 +694,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
 <span class="p">)</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.807 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.477 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 4544a752eb..055eb9b536 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>00:33.070</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:31.477</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>00:33.035</p></td>
+<td><p>00:31.441</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>
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 89279b0b61..56c32a9a51 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -567,9 +567,7 @@ for this template</p>
 waiting for device...
 device available
 Get devices for measurement successfully!
-No: 1   GFLOPS: 62.40/62.40     result: MeasureResult(costs=(0.003710196272727273,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.506129264831543, timestamp=1668612674.5134175)        [(&#39;tile_f&#39;, [-1, 8, 4, 4]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#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;, 1500), (&#39;unroll_explicit&#39;, 0)],None,4520238
-No: 2   GFLOPS: 46.81/62.40     result: MeasureResult(costs=(0.004945171857142857,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.2848103046417236, timestamp=1668612676.0735888)       [(&#39;tile_f&#39;, [-1, 4, 16, 2]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 1, 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;, 0)],None,4185807
-No: 3   GFLOPS: 0.00/62.40      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 588, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 540, in _build_func_common
@@ -691,8 +689,8 @@ 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 871, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 64, 4, 1]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 7]), (&#39;tile_rc&#39;, [-1, 8, 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;, 0)],None,4948265
-No: 4   GFLOPS: 0.00/62.40      result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 2, 32, 2]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 2, 64]), (&#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,3647031
+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 588, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 540, in _build_func_common
@@ -814,9 +812,9 @@ 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 871, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 1, 32, 16]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 7]), (&#39;tile_rc&#39;, [-1, 128, 4]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 0)],None,3192384
-No: 5   GFLOPS: 4.12/62.40      result: MeasureResult(costs=(0.05621964625,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.726212501525879, timestamp=1668612679.9325876)       [(&#39;tile_f&#39;, [-1, 8, 4, 8]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 4, 4]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 0)],None,74952
-No: 6   GFLOPS: 0.00/62.40      result: Traceback (most recent call last):
+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, 2, 256]), (&#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,5803149
+No: 3   GFLOPS: 228.85/228.85   result: MeasureResult(costs=(0.0010115684646464648,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.749254941940308, timestamp=1668618422.8077989)       [(&#39;tile_f&#39;, [-1, 4, 2, 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, 1, 3]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 1)],None,7984692
+No: 4   GFLOPS: 0.00/228.85     result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 588, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 540, in _build_func_common
@@ -938,10 +936,8 @@ 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 871, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 16, 4, 1]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 8, 8]), (&#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,5528183
-No: 7   GFLOPS: 200.02/200.02   result: MeasureResult(costs=(0.001157369597122302,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7944960594177246, timestamp=1668612681.7724178)       [(&#39;tile_f&#39;, [-1, 1, 16, 1]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 1, 32]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 1)],None,8467394
-No: 8   GFLOPS: 87.19/200.02    result: MeasureResult(costs=(0.0026551532195121953,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1284987926483154, timestamp=1668612682.474605)       [(&#39;tile_f&#39;, [-1, 1, 2, 2]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 4, 16]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 0)],None,127224
-No: 9   GFLOPS: 0.00/200.02     result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 1, 128, 4]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 16, 32]), (&#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,350595
+No: 5   GFLOPS: 0.00/228.85     result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 588, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 540, in _build_func_common
@@ -1063,10 +1059,9 @@ 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 871, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 1, 32, 1]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 2, 64]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 1)],None,7907720
-No: 10  GFLOPS: 46.96/200.02    result: MeasureResult(costs=(0.004929517181818182,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.243342876434326, timestamp=1668612685.9050357)        [(&#39;tile_f&#39;, [-1, 1, 2, 1]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 16, 8]), (&#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,3789950
-No: 11  GFLOPS: 413.73/413.73   result: MeasureResult(costs=(0.0005595513016759776,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5997123718261719, timestamp=1668612686.585363)       [(&#39;tile_f&#39;, [-1, 8, 4, 1]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 2, 2]), (&#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;, 1)],None,7978322
-No: 12  GFLOPS: 0.00/413.73     result: Traceback (most recent call last):
+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, 7]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 2, 64]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 1)],None,9650018
+No: 6   GFLOPS: 126.37/228.85   result: MeasureResult(costs=(0.001831866727272727,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.34965181350708, timestamp=1668618425.2790372) [(&#39;tile_f&#39;, [-1, 1, 4, 4]), (&#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, 3]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 0)],None,2177455
+No: 7   GFLOPS: 0.00/228.85     result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 588, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 540, in _build_func_common
@@ -1188,8 +1183,8 @@ 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 871, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 8, 16, 1]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 1, 16]), (&#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,2832097
-No: 13  GFLOPS: 0.00/413.73     result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 16, 4, 4]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 8, 16]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 1)],None,7101279
+No: 8   GFLOPS: 0.00/228.85     result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 588, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 540, in _build_func_common
@@ -1311,8 +1306,8 @@ 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 871, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 32, 4, 4]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 7]), (&#39;tile_rc&#39;, [-1, 32, 4]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 1)],None,7831240
-No: 14  GFLOPS: 0.00/413.73     result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 2, 128, 2]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 7]), (&#39;tile_rc&#39;, [-1, 32, 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,5089138
+No: 9   GFLOPS: 0.00/228.85     result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 588, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 540, in _build_func_common
@@ -1434,8 +1429,8 @@ 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 871, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 1, 2, 64]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#39;tile_x&#39;, [-1, 1, 1, 7]), (&#39;tile_rc&#39;, [-1, 32, 1]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 0)],None,4861104
-No: 15  GFLOPS: 0.00/413.73     result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 32, 4, 4]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 8, 64]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 0)],None,943480
+No: 10  GFLOPS: 0.00/228.85     result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 588, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 540, in _build_func_common
@@ -1557,8 +1552,8 @@ 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 871, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 16, 8, 1]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 128, 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;, 1)],None,7030351
-No: 16  GFLOPS: 0.00/413.73     result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 4, 64, 2]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 1, 32]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 1)],None,7111376
+No: 11  GFLOPS: 0.00/228.85     result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 588, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 540, in _build_func_common
@@ -1680,8 +1675,8 @@ 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 871, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 64, 1, 4]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#39;tile_x&#39;, [-1, 1, 1, 7]), (&#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;, 0)],None,2939086
-No: 17  GFLOPS: 0.00/413.73     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, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 64, 2]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 1)],None,8769711
+No: 12  GFLOPS: 0.00/228.85     result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 588, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 540, in _build_func_common
@@ -1803,8 +1798,8 @@ 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 871, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 1, 1, 256]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 7]), (&#39;tile_rc&#39;, [-1, 4, 2]), (&#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,10112296
-No: 18  GFLOPS: 0.00/413.73     result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 1, 128, 4]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 32, 8]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 1)],None,8437575
+No: 13  GFLOPS: 0.00/228.85     result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 588, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 540, in _build_func_common
@@ -1926,9 +1921,8 @@ 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 871, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 32, 8, 2]), (&#39;tile_y&#39;, [-1, 7, 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, 3, 1]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 0)],None,4543744
-No: 19  GFLOPS: 439.07/439.07   result: MeasureResult(costs=(0.000527258671875,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0887837409973145, timestamp=1668612689.1139297)  [(&#39;tile_f&#39;, [-1, 1, 2, 8]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 1, 4]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 1)],None,9168643
-No: 20  GFLOPS: 0.00/439.07     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, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 4, 32]), (&#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,6925666
+No: 14  GFLOPS: 0.00/228.85     result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 588, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 540, in _build_func_common
@@ -2050,7 +2044,379 @@ 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 871, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 2, 128, 1]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 8, 32]), (&#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,10412870
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 1, 1, 512]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 4, 64]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 0)],None,2489299
+No: 15  GFLOPS: 0.00/228.85     result: Traceback (most recent call last):
+  File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 588, in __call__
+    func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+  File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 540, in _build_func_common
+    func = build(s, args, target_host=task.target_host, runtime=runtime)
+  File &quot;/workspace/python/tvm/driver/build_module.py&quot;, line 227, in build
+    input_mod = lower(inputs, args, name=name, binds=binds)
+  File &quot;/workspace/python/tvm/driver/build_module.py&quot;, line 134, in lower
+    return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+  File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+  File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 276, in tvm._ffi._cy3.core.FuncCall
+  File &quot;tvm/_ffi/_cython/./base.pxi&quot;, line 181, in tvm._ffi._cy3.core.CHECK_CALL
+tvm._ffi.base.TVMError: Traceback (most recent call last):
+  24: TVMFuncCall
+        at ../src/runtime/c_runtime_api.cc:477
+  23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+        at ../include/tvm/runtime/packed_func.h:1217
+  22: Call
+        at ../include/tvm/runtime/packed_func.h:1213
+  21: operator()
+        at ../include/tvm/runtime/packed_func.h:1731
+  20: unpack_call&lt;tvm::IRModule, 5, tvm::&lt;lambda(tvm::te::Schedule, const tvm::runtime::Array&lt;tvm::runtime::ObjectRef&gt;&amp;, const tvm::runtime::String&amp;, const tvm::runtime::Map&lt;tvm::te::Tensor, tvm::tir::Buffer&gt;&amp;, bool)&gt; &gt;
+        at ../include/tvm/runtime/packed_func.h:1671
+  19: run&lt;&gt;
+        at ../include/tvm/runtime/packed_func.h:1631
+  18: run&lt;tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1631
+  17: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1631
+  16: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1631
+  15: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1631
+  14: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1646
+  13: operator()
+        at ../src/driver/driver_api.cc:388
+  12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array&lt;tvm::runtime::ObjectRef, void&gt; const&amp;, std::__cxx11::basic_string&lt;char, std::char_traits&lt;char&gt;, std::allocator&lt;char&gt; &gt; const&amp;, std::unordered_map&lt;tvm::te::Tensor, tvm::tir::Buffer, std::hash&lt;tvm::te::Tensor&gt;, std::equal_to&lt;tvm::te::Tensor&gt;, std::allocator&lt;std::pair&lt;tvm::te::Tensor const, tvm::tir::Buffer&gt; &gt; &gt; const&amp;, tvm::GlobalVarSupply, bool)
+        at ../src/driver/driver_api.cc:374
+  11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array&lt;tvm::transform::Pass, void&gt;)
+        at ../src/driver/driver_api.cc:269
+  10: tvm::transform::Pass::operator()(tvm::IRModule) const
+        at ../src/ir/transform.cc:258
+  9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/ir/transform.cc:274
+  8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/ir/transform.cc:453
+  7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/ir/transform.cc:274
+  6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/tir/ir/transform.cc:100
+  5: tvm::runtime::TypedPackedFunc&lt;tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)&gt;::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+        at ../include/tvm/runtime/packed_func.h:1750
+  4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher&lt;tvm::tir::PrimFunc&gt;::run&lt;tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext&gt;(tvm::runtime::PackedFunc const&amp;, tvm::tir::PrimFunc&amp;&amp;, tvm::IRModule&amp;&amp;, tvm::transform::PassContext&amp;&amp;)
+        at ../include/tvm/runtime/packed_func.h:1694
+  3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()&lt;tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext&gt;(tvm::tir::PrimFunc&amp;&amp;, tvm::IRModule&amp;&amp;, tvm::transform::PassContext&amp;&amp;) const
+        at ../include/tvm/runtime/packed_func.h:1618
+  2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+        at ../include/tvm/runtime/packed_func.h:1217
+  1: Call
+        at ../include/tvm/runtime/packed_func.h:1213
+  0: operator()
+        at ../src/runtime/c_runtime_api.cc:534
+  File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 56, in tvm._ffi._cy3.core.tvm_callback
+  File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 871, in verify_pass
+    raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
+
+Traceback (most recent call last):
+  24: TVMFuncCall
+        at ../src/runtime/c_runtime_api.cc:477
+  23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+        at ../include/tvm/runtime/packed_func.h:1217
+  22: Call
+        at ../include/tvm/runtime/packed_func.h:1213
+  21: operator()
+        at ../include/tvm/runtime/packed_func.h:1731
+  20: unpack_call&lt;tvm::IRModule, 5, tvm::&lt;lambda(tvm::te::Schedule, const tvm::runtime::Array&lt;tvm::runtime::ObjectRef&gt;&amp;, const tvm::runtime::String&amp;, const tvm::runtime::Map&lt;tvm::te::Tensor, tvm::tir::Buffer&gt;&amp;, bool)&gt; &gt;
+        at ../include/tvm/runtime/packed_func.h:1671
+  19: run&lt;&gt;
+        at ../include/tvm/runtime/packed_func.h:1631
+  18: run&lt;tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1631
+  17: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1631
+  16: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1631
+  15: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1631
+  14: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1646
+  13: operator()
+        at ../src/driver/driver_api.cc:388
+  12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array&lt;tvm::runtime::ObjectRef, void&gt; const&amp;, std::__cxx11::basic_string&lt;char, std::char_traits&lt;char&gt;, std::allocator&lt;char&gt; &gt; const&amp;, std::unordered_map&lt;tvm::te::Tensor, tvm::tir::Buffer, std::hash&lt;tvm::te::Tensor&gt;, std::equal_to&lt;tvm::te::Tensor&gt;, std::allocator&lt;std::pair&lt;tvm::te::Tensor const, tvm::tir::Buffer&gt; &gt; &gt; const&amp;, tvm::GlobalVarSupply, bool)
+        at ../src/driver/driver_api.cc:374
+  11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array&lt;tvm::transform::Pass, void&gt;)
+        at ../src/driver/driver_api.cc:269
+  10: tvm::transform::Pass::operator()(tvm::IRModule) const
+        at ../src/ir/transform.cc:258
+  9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/ir/transform.cc:274
+  8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/ir/transform.cc:453
+  7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/ir/transform.cc:274
+  6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/tir/ir/transform.cc:100
+  5: tvm::runtime::TypedPackedFunc&lt;tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)&gt;::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+        at ../include/tvm/runtime/packed_func.h:1750
+  4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher&lt;tvm::tir::PrimFunc&gt;::run&lt;tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext&gt;(tvm::runtime::PackedFunc const&amp;, tvm::tir::PrimFunc&amp;&amp;, tvm::IRModule&amp;&amp;, tvm::transform::PassContext&amp;&amp;)
+        at ../include/tvm/runtime/packed_func.h:1694
+  3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()&lt;tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext&gt;(tvm::tir::PrimFunc&amp;&amp;, tvm::IRModule&amp;&amp;, tvm::transform::PassContext&amp;&amp;) const
+        at ../include/tvm/runtime/packed_func.h:1618
+  2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+        at ../include/tvm/runtime/packed_func.h:1217
+  1: Call
+        at ../include/tvm/runtime/packed_func.h:1213
+  0: operator()
+        at ../src/runtime/c_runtime_api.cc:534
+  File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 56, in tvm._ffi._cy3.core.tvm_callback
+  File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 871, in verify_pass
+    raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 256, 2, 1]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 7]), (&#39;tile_rc&#39;, [-1, 16, 32]), (&#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,2867938
+No: 16  GFLOPS: 0.00/228.85     result: Traceback (most recent call last):
+  File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 588, in __call__
+    func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+  File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 540, in _build_func_common
+    func = build(s, args, target_host=task.target_host, runtime=runtime)
+  File &quot;/workspace/python/tvm/driver/build_module.py&quot;, line 227, in build
+    input_mod = lower(inputs, args, name=name, binds=binds)
+  File &quot;/workspace/python/tvm/driver/build_module.py&quot;, line 134, in lower
+    return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+  File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+  File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 276, in tvm._ffi._cy3.core.FuncCall
+  File &quot;tvm/_ffi/_cython/./base.pxi&quot;, line 181, in tvm._ffi._cy3.core.CHECK_CALL
+tvm._ffi.base.TVMError: Traceback (most recent call last):
+  24: TVMFuncCall
+        at ../src/runtime/c_runtime_api.cc:477
+  23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+        at ../include/tvm/runtime/packed_func.h:1217
+  22: Call
+        at ../include/tvm/runtime/packed_func.h:1213
+  21: operator()
+        at ../include/tvm/runtime/packed_func.h:1731
+  20: unpack_call&lt;tvm::IRModule, 5, tvm::&lt;lambda(tvm::te::Schedule, const tvm::runtime::Array&lt;tvm::runtime::ObjectRef&gt;&amp;, const tvm::runtime::String&amp;, const tvm::runtime::Map&lt;tvm::te::Tensor, tvm::tir::Buffer&gt;&amp;, bool)&gt; &gt;
+        at ../include/tvm/runtime/packed_func.h:1671
+  19: run&lt;&gt;
+        at ../include/tvm/runtime/packed_func.h:1631
+  18: run&lt;tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1631
+  17: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1631
+  16: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1631
+  15: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1631
+  14: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1646
+  13: operator()
+        at ../src/driver/driver_api.cc:388
+  12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array&lt;tvm::runtime::ObjectRef, void&gt; const&amp;, std::__cxx11::basic_string&lt;char, std::char_traits&lt;char&gt;, std::allocator&lt;char&gt; &gt; const&amp;, std::unordered_map&lt;tvm::te::Tensor, tvm::tir::Buffer, std::hash&lt;tvm::te::Tensor&gt;, std::equal_to&lt;tvm::te::Tensor&gt;, std::allocator&lt;std::pair&lt;tvm::te::Tensor const, tvm::tir::Buffer&gt; &gt; &gt; const&amp;, tvm::GlobalVarSupply, bool)
+        at ../src/driver/driver_api.cc:374
+  11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array&lt;tvm::transform::Pass, void&gt;)
+        at ../src/driver/driver_api.cc:269
+  10: tvm::transform::Pass::operator()(tvm::IRModule) const
+        at ../src/ir/transform.cc:258
+  9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/ir/transform.cc:274
+  8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/ir/transform.cc:453
+  7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/ir/transform.cc:274
+  6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/tir/ir/transform.cc:100
+  5: tvm::runtime::TypedPackedFunc&lt;tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)&gt;::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+        at ../include/tvm/runtime/packed_func.h:1750
+  4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher&lt;tvm::tir::PrimFunc&gt;::run&lt;tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext&gt;(tvm::runtime::PackedFunc const&amp;, tvm::tir::PrimFunc&amp;&amp;, tvm::IRModule&amp;&amp;, tvm::transform::PassContext&amp;&amp;)
+        at ../include/tvm/runtime/packed_func.h:1694
+  3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()&lt;tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext&gt;(tvm::tir::PrimFunc&amp;&amp;, tvm::IRModule&amp;&amp;, tvm::transform::PassContext&amp;&amp;) const
+        at ../include/tvm/runtime/packed_func.h:1618
+  2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+        at ../include/tvm/runtime/packed_func.h:1217
+  1: Call
+        at ../include/tvm/runtime/packed_func.h:1213
+  0: operator()
+        at ../src/runtime/c_runtime_api.cc:534
+  File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 56, in tvm._ffi._cy3.core.tvm_callback
+  File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 871, in verify_pass
+    raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
+
+Traceback (most recent call last):
+  24: TVMFuncCall
+        at ../src/runtime/c_runtime_api.cc:477
+  23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+        at ../include/tvm/runtime/packed_func.h:1217
+  22: Call
+        at ../include/tvm/runtime/packed_func.h:1213
+  21: operator()
+        at ../include/tvm/runtime/packed_func.h:1731
+  20: unpack_call&lt;tvm::IRModule, 5, tvm::&lt;lambda(tvm::te::Schedule, const tvm::runtime::Array&lt;tvm::runtime::ObjectRef&gt;&amp;, const tvm::runtime::String&amp;, const tvm::runtime::Map&lt;tvm::te::Tensor, tvm::tir::Buffer&gt;&amp;, bool)&gt; &gt;
+        at ../include/tvm/runtime/packed_func.h:1671
+  19: run&lt;&gt;
+        at ../include/tvm/runtime/packed_func.h:1631
+  18: run&lt;tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1631
+  17: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1631
+  16: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1631
+  15: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1631
+  14: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1646
+  13: operator()
+        at ../src/driver/driver_api.cc:388
+  12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array&lt;tvm::runtime::ObjectRef, void&gt; const&amp;, std::__cxx11::basic_string&lt;char, std::char_traits&lt;char&gt;, std::allocator&lt;char&gt; &gt; const&amp;, std::unordered_map&lt;tvm::te::Tensor, tvm::tir::Buffer, std::hash&lt;tvm::te::Tensor&gt;, std::equal_to&lt;tvm::te::Tensor&gt;, std::allocator&lt;std::pair&lt;tvm::te::Tensor const, tvm::tir::Buffer&gt; &gt; &gt; const&amp;, tvm::GlobalVarSupply, bool)
+        at ../src/driver/driver_api.cc:374
+  11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array&lt;tvm::transform::Pass, void&gt;)
+        at ../src/driver/driver_api.cc:269
+  10: tvm::transform::Pass::operator()(tvm::IRModule) const
+        at ../src/ir/transform.cc:258
+  9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/ir/transform.cc:274
+  8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/ir/transform.cc:453
+  7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/ir/transform.cc:274
+  6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/tir/ir/transform.cc:100
+  5: tvm::runtime::TypedPackedFunc&lt;tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)&gt;::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+        at ../include/tvm/runtime/packed_func.h:1750
+  4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher&lt;tvm::tir::PrimFunc&gt;::run&lt;tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext&gt;(tvm::runtime::PackedFunc const&amp;, tvm::tir::PrimFunc&amp;&amp;, tvm::IRModule&amp;&amp;, tvm::transform::PassContext&amp;&amp;)
+        at ../include/tvm/runtime/packed_func.h:1694
+  3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()&lt;tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext&gt;(tvm::tir::PrimFunc&amp;&amp;, tvm::IRModule&amp;&amp;, tvm::transform::PassContext&amp;&amp;) const
+        at ../include/tvm/runtime/packed_func.h:1618
+  2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+        at ../include/tvm/runtime/packed_func.h:1217
+  1: Call
+        at ../include/tvm/runtime/packed_func.h:1213
+  0: operator()
+        at ../src/runtime/c_runtime_api.cc:534
+  File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 56, in tvm._ffi._cy3.core.tvm_callback
+  File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 871, in verify_pass
+    raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 1, 256, 2]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 1, 64]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 1)],None,9065199
+No: 17  GFLOPS: 53.80/228.85    result: MeasureResult(costs=(0.00430309384,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4398438930511475, timestamp=1668618429.2793698)      [(&#39;tile_f&#39;, [-1, 1, 64, 8]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 2, 1]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 1)],None,6780343
+No: 18  GFLOPS: 0.00/228.85     result: Traceback (most recent call last):
+  File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 588, in __call__
+    func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+  File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 540, in _build_func_common
+    func = build(s, args, target_host=task.target_host, runtime=runtime)
+  File &quot;/workspace/python/tvm/driver/build_module.py&quot;, line 227, in build
+    input_mod = lower(inputs, args, name=name, binds=binds)
+  File &quot;/workspace/python/tvm/driver/build_module.py&quot;, line 134, in lower
+    return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+  File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+  File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 276, in tvm._ffi._cy3.core.FuncCall
+  File &quot;tvm/_ffi/_cython/./base.pxi&quot;, line 181, in tvm._ffi._cy3.core.CHECK_CALL
+tvm._ffi.base.TVMError: Traceback (most recent call last):
+  24: TVMFuncCall
+        at ../src/runtime/c_runtime_api.cc:477
+  23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+        at ../include/tvm/runtime/packed_func.h:1217
+  22: Call
+        at ../include/tvm/runtime/packed_func.h:1213
+  21: operator()
+        at ../include/tvm/runtime/packed_func.h:1731
+  20: unpack_call&lt;tvm::IRModule, 5, tvm::&lt;lambda(tvm::te::Schedule, const tvm::runtime::Array&lt;tvm::runtime::ObjectRef&gt;&amp;, const tvm::runtime::String&amp;, const tvm::runtime::Map&lt;tvm::te::Tensor, tvm::tir::Buffer&gt;&amp;, bool)&gt; &gt;
+        at ../include/tvm/runtime/packed_func.h:1671
+  19: run&lt;&gt;
+        at ../include/tvm/runtime/packed_func.h:1631
+  18: run&lt;tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1631
+  17: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1631
+  16: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1631
+  15: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1631
+  14: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1646
+  13: operator()
+        at ../src/driver/driver_api.cc:388
+  12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array&lt;tvm::runtime::ObjectRef, void&gt; const&amp;, std::__cxx11::basic_string&lt;char, std::char_traits&lt;char&gt;, std::allocator&lt;char&gt; &gt; const&amp;, std::unordered_map&lt;tvm::te::Tensor, tvm::tir::Buffer, std::hash&lt;tvm::te::Tensor&gt;, std::equal_to&lt;tvm::te::Tensor&gt;, std::allocator&lt;std::pair&lt;tvm::te::Tensor const, tvm::tir::Buffer&gt; &gt; &gt; const&amp;, tvm::GlobalVarSupply, bool)
+        at ../src/driver/driver_api.cc:374
+  11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array&lt;tvm::transform::Pass, void&gt;)
+        at ../src/driver/driver_api.cc:269
+  10: tvm::transform::Pass::operator()(tvm::IRModule) const
+        at ../src/ir/transform.cc:258
+  9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/ir/transform.cc:274
+  8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/ir/transform.cc:453
+  7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/ir/transform.cc:274
+  6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/tir/ir/transform.cc:100
+  5: tvm::runtime::TypedPackedFunc&lt;tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)&gt;::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+        at ../include/tvm/runtime/packed_func.h:1750
+  4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher&lt;tvm::tir::PrimFunc&gt;::run&lt;tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext&gt;(tvm::runtime::PackedFunc const&amp;, tvm::tir::PrimFunc&amp;&amp;, tvm::IRModule&amp;&amp;, tvm::transform::PassContext&amp;&amp;)
+        at ../include/tvm/runtime/packed_func.h:1694
+  3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()&lt;tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext&gt;(tvm::tir::PrimFunc&amp;&amp;, tvm::IRModule&amp;&amp;, tvm::transform::PassContext&amp;&amp;) const
+        at ../include/tvm/runtime/packed_func.h:1618
+  2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+        at ../include/tvm/runtime/packed_func.h:1217
+  1: Call
+        at ../include/tvm/runtime/packed_func.h:1213
+  0: operator()
+        at ../src/runtime/c_runtime_api.cc:534
+  File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 56, in tvm._ffi._cy3.core.tvm_callback
+  File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 871, in verify_pass
+    raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
+
+Traceback (most recent call last):
+  24: TVMFuncCall
+        at ../src/runtime/c_runtime_api.cc:477
+  23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+        at ../include/tvm/runtime/packed_func.h:1217
+  22: Call
+        at ../include/tvm/runtime/packed_func.h:1213
+  21: operator()
+        at ../include/tvm/runtime/packed_func.h:1731
+  20: unpack_call&lt;tvm::IRModule, 5, tvm::&lt;lambda(tvm::te::Schedule, const tvm::runtime::Array&lt;tvm::runtime::ObjectRef&gt;&amp;, const tvm::runtime::String&amp;, const tvm::runtime::Map&lt;tvm::te::Tensor, tvm::tir::Buffer&gt;&amp;, bool)&gt; &gt;
+        at ../include/tvm/runtime/packed_func.h:1671
+  19: run&lt;&gt;
+        at ../include/tvm/runtime/packed_func.h:1631
+  18: run&lt;tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1631
+  17: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1631
+  16: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1631
+  15: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1631
+  14: run&lt;tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_&gt;
+        at ../include/tvm/runtime/packed_func.h:1646
+  13: operator()
+        at ../src/driver/driver_api.cc:388
+  12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array&lt;tvm::runtime::ObjectRef, void&gt; const&amp;, std::__cxx11::basic_string&lt;char, std::char_traits&lt;char&gt;, std::allocator&lt;char&gt; &gt; const&amp;, std::unordered_map&lt;tvm::te::Tensor, tvm::tir::Buffer, std::hash&lt;tvm::te::Tensor&gt;, std::equal_to&lt;tvm::te::Tensor&gt;, std::allocator&lt;std::pair&lt;tvm::te::Tensor const, tvm::tir::Buffer&gt; &gt; &gt; const&amp;, tvm::GlobalVarSupply, bool)
+        at ../src/driver/driver_api.cc:374
+  11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array&lt;tvm::transform::Pass, void&gt;)
+        at ../src/driver/driver_api.cc:269
+  10: tvm::transform::Pass::operator()(tvm::IRModule) const
+        at ../src/ir/transform.cc:258
+  9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/ir/transform.cc:274
+  8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/ir/transform.cc:453
+  7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/ir/transform.cc:274
+  6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&amp;) const
+        at ../src/tir/ir/transform.cc:100
+  5: tvm::runtime::TypedPackedFunc&lt;tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)&gt;::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+        at ../include/tvm/runtime/packed_func.h:1750
+  4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher&lt;tvm::tir::PrimFunc&gt;::run&lt;tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext&gt;(tvm::runtime::PackedFunc const&amp;, tvm::tir::PrimFunc&amp;&amp;, tvm::IRModule&amp;&amp;, tvm::transform::PassContext&amp;&amp;)
+        at ../include/tvm/runtime/packed_func.h:1694
+  3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()&lt;tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext&gt;(tvm::tir::PrimFunc&amp;&amp;, tvm::IRModule&amp;&amp;, tvm::transform::PassContext&amp;&amp;) const
+        at ../include/tvm/runtime/packed_func.h:1618
+  2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+        at ../include/tvm/runtime/packed_func.h:1217
+  1: Call
+        at ../include/tvm/runtime/packed_func.h:1213
+  0: operator()
+        at ../src/runtime/c_runtime_api.cc:534
+  File &quot;tvm/_ffi/_cython/./packed_func.pxi&quot;, line 56, in tvm._ffi._cy3.core.tvm_callback
+  File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 871, in verify_pass
+    raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 4, 4, 16]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 64, 2]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 0)],None,639717
+No: 19  GFLOPS: 37.57/228.85    result: MeasureResult(costs=(0.006161984117647059,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3533060550689697, timestamp=1668618430.00153) [(&#39;tile_f&#39;, [-1, 32, 2, 1]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 4, 2]), (&#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,5658415
+No: 20  GFLOPS: 2.70/228.85     result: MeasureResult(costs=(0.085883934,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.988248109817505, timestamp=1668618431.4606593) [(&#39;tile_f&#39;, [-1, 32, 2, 1]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 7]), (&#39;tile_rc&#39;, [-1, 1, 2]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 0)],None,2554875
 </pre></div>
 </div>
 <p>Finally we can inspect the best config from log file, check correctness,
@@ -2089,9 +2455,9 @@ 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, 1, 2, 8]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 1, 4]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 1)],None,9168643
+[(&#39;tile_f&#39;, [-1, 4, 2, 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, 1, 3]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 1)],None,7984692
 Finish loading 20 records
-Time cost of this operator: 0.000886
+Time cost of this operator: 0.000809
 </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 b6a2141034..9420514b7c 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -596,10 +596,10 @@ the tuned operator.</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build without Autotuning ##########
 Node Name                                     Ops                                           Time(us)  Time(%)  Shape              Inputs  Outputs  Measurements(us)
 ---------                                     ---                                           --------  -------  -----              ------  -------  ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  311.8     98.714   (1, 2, 10, 10, 3)  2       1        [311.8]
-tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       3.102     0.982    (1, 6, 10, 10)     1       1        [3.102]
-tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.962     0.305    (1, 1, 10, 10, 3)  1       1        [0.962]
-Total_time                                    -                                             315.863   -        -                  -       -        -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  313.9     98.712   (1, 2, 10, 10, 3)  2       1        [313.9]
+tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       3.131     0.985    (1, 6, 10, 10)     1       1        [3.131]
+tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.964     0.303    (1, 1, 10, 10, 3)  1       1        [0.964]
+Total_time                                    -                                             317.996   -        -                  -       -        -
 </pre></div>
 </div>
 </div>
@@ -650,10 +650,10 @@ 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  106.6     97.612   (1, 6, 10, 10, 1)  2       1        [106.6]
-tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       1.77      1.621    (1, 6, 10, 10)     1       1        [1.77]
-tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.838     0.767    (1, 3, 10, 10, 1)  1       1        [0.838]
-Total_time                                    -                                             109.208   -        -                  -       -        -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  102.6     97.476   (1, 6, 10, 10, 1)  2       1        [102.6]
+tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       1.799     1.709    (1, 6, 10, 10)     1       1        [1.799]
+tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.858     0.815    (1, 3, 10, 10, 1)  1       1        [0.858]
+Total_time                                    -                                             105.257   -        -                  -       -        -
 </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 213b685950..3f71482e11 100644
--- a/docs/how_to/work_with_microtvm/micro_pytorch.html
+++ b/docs/how_to/work_with_microtvm/micro_pytorch.html
@@ -440,7 +440,7 @@ download a cat image and preprocess it to use as the model input.</p>
 Downloading: &quot;https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth&quot; to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
 
   0%|          | 0.00/3.42M [00:00&lt;?, ?B/s]
-100%|##########| 3.42M/3.42M [00:00&lt;00:00, 81.3MB/s]
+100%|##########| 3.42M/3.42M [00:00&lt;00:00, 75.6MB/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.
@@ -564,7 +564,7 @@ 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  6.472 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  4.241 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 fe8e82864b..1a27ffe458 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -530,7 +530,7 @@ 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/tmpy5o6f33_/images/random&#39;
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>&#39;/tmp/tmpbz6hkicy/images/random&#39;
 </pre></div>
 </div>
 </div>
@@ -590,8 +590,8 @@ 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], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [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/tmpy5o6f33_/images/target contains 8144 images
-/tmp/tmpy5o6f33_/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], [1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpbz6hkicy/images/target contains 8144 images
+/tmp/tmpbz6hkicy/images/random contains 5000 images
 </pre></div>
 </div>
 </div>
@@ -703,13 +703,13 @@ 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: 0.2249 - accuracy: 0.9236 - val_loss: 0.1049 - val_accuracy: 0.9603 - 47s/epoch - 144ms/step
+328/328 - 47s - loss: 0.2374 - accuracy: 0.9209 - val_loss: 0.1806 - val_accuracy: 0.9388 - 47s/epoch - 143ms/step
 Epoch 2/3
-328/328 - 43s - loss: 0.1043 - accuracy: 0.9625 - val_loss: 0.1249 - val_accuracy: 0.9596 - 43s/epoch - 133ms/step
+328/328 - 44s - loss: 0.1106 - accuracy: 0.9570 - val_loss: 0.0969 - val_accuracy: 0.9641 - 44s/epoch - 133ms/step
 Epoch 3/3
-328/328 - 43s - loss: 0.0645 - accuracy: 0.9761 - val_loss: 0.1150 - val_accuracy: 0.9656 - 43s/epoch - 132ms/step
+328/328 - 43s - loss: 0.0756 - accuracy: 0.9724 - val_loss: 0.0981 - val_accuracy: 0.9690 - 43s/epoch - 132ms/step
 
-&lt;keras.callbacks.History object at 0x7f09494f4550&gt;
+&lt;keras.callbacks.History object at 0x7f5cc00bee90&gt;
 </pre></div>
 </div>
 </div>
@@ -971,7 +971,7 @@ as intended.</p>
 <p>From here, we could modify the model to read live images from the camera - we have another
 Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
 <a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes  38.542 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes  47.987 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 1518cb0ff7..3a8020d28a 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>06:48.119</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>06:54.261</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 83%" />
@@ -349,19 +349,19 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>04:38.542</p></td>
+<td><p>04:47.987</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>01:06.472</p></td>
+<td><p>01:04.241</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>00:50.409</p></td>
+<td><p>00:49.982</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>00:08.910</p></td>
+<td><p>00:08.264</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>
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 4df9fd21dd..e11bb722c8 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>00:44.620</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:43.314</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>00:32.524</p></td>
+<td><p>00:31.790</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>00:10.560</p></td>
+<td><p>00:10.146</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="build_gcn.html#sphx-glr-how-to-work-with-relay-build-gcn-py"><span class="std std-ref">Building a Graph Convolutional Network</span></a> (<code class="docutils literal notranslate"><span class="pre">build_gcn.py</span></code>)</p></td>
-<td><p>00:01.529</p></td>
+<td><p>00:01.372</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 49e5bd0f55..c388b9c6cb 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 0x7f0949fdbdd0&gt;
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>&lt;function my_cuda_math_rule at 0x7f5cc13808c0&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 c27eaba1b5..2aab511e27 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>00:07.650</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:07.373</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 83%" />
@@ -349,11 +349,11 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:05.341</p></td>
+<td><p>00:05.026</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="tensorize.html#sphx-glr-how-to-work-with-schedules-tensorize-py"><span class="std std-ref">Use Tensorize to Leverage Hardware Intrinsics</span></a> (<code class="docutils literal notranslate"><span class="pre">tensorize.py</span></code>)</p></td>
-<td><p>00:00.986</p></td>
+<td><p>00:01.043</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>
@@ -361,23 +361,23 @@
 <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>00:00.542</p></td>
+<td><p>00:00.535</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>00:00.117</p></td>
+<td><p>00:00.116</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>00:00.055</p></td>
+<td><p>00:00.049</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>00:00.033</p></td>
+<td><p>00:00.029</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>
-<td><p>00:00.021</p></td>
+<td><p>00:00.019</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 </tbody>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index a579c1eafd..a1a1d3fbe0 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -586,7 +586,7 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
              B: Buffer(B_2: Pointer(float32), float32, [512, 64], []),
              C: Buffer(C_2: Pointer(float32), float32, [1024, 512], [])}
   buffer_map = {A_1: A, B_1: B, C_1: C} {
-  attr [IterVar(i: int32, (nullptr), &quot;DataPar&quot;, &quot;&quot;)] &quot;pragma_import_llvm&quot; = &quot;; ModuleID = &#39;/tmp/tmp9m2vzx82/input0.cc&#39;\nsource_filename = \&quot;/tmp/tmp9m2vzx82/input0.cc\&quot;\ntarget datalayout = \&quot;e-m:e-i64:64-f80:128-n8:16:32:64-S128\&quot;\ntarget triple = \&quot;x86_64-pc-linux-gnu\&quot;\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n  %7 = allo [...]
+  attr [IterVar(i: int32, (nullptr), &quot;DataPar&quot;, &quot;&quot;)] &quot;pragma_import_llvm&quot; = &quot;; ModuleID = &#39;/tmp/tmp0b8qkn1u/input0.cc&#39;\nsource_filename = \&quot;/tmp/tmp0b8qkn1u/input0.cc\&quot;\ntarget datalayout = \&quot;e-m:e-i64:64-f80:128-n8:16:32:64-S128\&quot;\ntarget triple = \&quot;x86_64-pc-linux-gnu\&quot;\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n  %7 = allo [...]
   for (i, 0, 1024) {
     for (j.outer: int32, 0, 32) {
       @tir.call_extern(&quot;gemv_update&quot;, @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index b7cfaf936a..86a37e1231 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 95072b1d34..7c304c0740 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/78b53221f/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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 5d689a2cd7..7fff7c266f 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/78b53221f/web/src/memory.ts#L223">memory.ts:223</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/memory.ts#L208">memory.ts:208</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/memory.ts#L312">memory.ts:312</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/memory.ts#L284">memory.ts:284</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/memory.ts#L388">memory.ts:388</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/memory.ts#L376">memory.ts:376</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/memory.ts#L267">memory.ts:267</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/memory.ts#L243">memory.ts:243</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/memory.ts#L321">memory.ts:321</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/memory.ts#L252">memory.ts:252</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/memory.ts#L359">memory.ts:359</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/memory.ts#L342">memory.ts:342</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/memory.ts#L350">memory.ts:350</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/memory.ts#L326">memory.ts:326</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/memory.ts#L363">memory.ts:363</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/memory.ts#L346">memory.ts:346</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/memory.ts#L334">memory.ts:334</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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 9fd83bd4f0..60b86565f7 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/78b53221f/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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 51d600ccac..f0d545637b 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/78b53221f/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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 26e1f5ee6c..a2322feef4 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/78b53221f/web/src/environment.ts#L86">environment.ts:86</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/environment.ts#L70">environment.ts:70</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/environment.ts#L69">environment.ts:69</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/environment.ts#L78">environment.ts:78</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/environment.ts#L84">environment.ts:84</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/environment.ts#L105">environment.ts:105</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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 ddcc13caa6..90d2b9759e 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/78b53221f/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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 2c4e115df6..5762841b2c 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/78b53221f/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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 f6e4d9491c..8023824a54 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/78b53221f/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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 f8339e67ab..b1f7857cb5 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/78b53221f/web/src/memory.ts#L40">memory.ts:40</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/memory.ts#L32">memory.ts:32</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/memory.ts#L33">memory.ts:33</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/memory.ts#L154">memory.ts:154</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/memory.ts#L90">memory.ts:90</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/memory.ts#L97">memory.ts:97</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/memory.ts#L74">memory.ts:74</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/memory.ts#L81">memory.ts:81</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/memory.ts#L104">memory.ts:104</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/memory.ts#L132">memory.ts:132</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/memory.ts#L145">memory.ts:145</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/memory.ts#L60">memory.ts:60</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/memory.ts#L67">memory.ts:67</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/memory.ts#L53">memory.ts:53</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/memory.ts#L114">memory.ts:114</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/memory.ts#L124">memory.ts:124</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/memory.ts#L175">memory.ts:175</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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 704084f337..9474ac1e19 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/78b53221f/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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 e3677adf3e..f076e0af7c 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/78b53221f/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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 b9debefc9c..af88505a4b 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/78b53221f/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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 8f395d8d01..02d681f2f1 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/78b53221f/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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 ec238236a8..333171887e 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/78b53221f/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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 fa97207634..245f826434 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/78b53221f/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/78b53221f/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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 f14f51665d..8d582641e6 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/78b53221f/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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 6bc098d33d..b79f365c8b 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/78b53221f/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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 352513a6cb..63af544e06 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/78b53221f/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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 bd9d7eb903..1f55842ba6 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/78b53221f/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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 1996e2239d..335fa6ad3b 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/78b53221f/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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 4d52532099..429a388133 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/78b53221f/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/support.ts#L25">support.ts:25</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/support.ts#L39">support.ts:39</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/support.ts#L52">support.ts:52</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/compact.ts#L38">compact.ts:38</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/environment.ts#L32">environment.ts:32</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/compact.ts#L24">compact.ts:24</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/support.ts#L62">support.ts:62</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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 a7ff467589..526afbbf48 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/78b53221f/web/src/types.ts#L52">types.ts:52</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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 480e3a5f57..fd0802fe81 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/78b53221f/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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 0f4376f4e6..2f862297d1 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/78b53221f/web/src/types.ts#L34">types.ts:34</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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/78b53221f/web/src/types.ts#L39">types.ts:39</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/44ed06ac9/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 6dc9ac06e5..215399390c 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 a30afe1c88..81fbb2cd06 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>00:27.455</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:26.589</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>00:27.449</p></td>
+<td><p>00:26.582</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 3acde99069..d0ef38eeaf 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -582,7 +582,7 @@ 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 31.70s!
+resnet18_v1 inference graph built in 29.82s!
 </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 ac28f12055..067f3bc0c0 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -600,7 +600,7 @@ 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 20.16s!
+yolov3-tiny inference graph built in 20.23s!
 </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 ea2283f93c..1cb3a65b4d 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>01:44.215</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:42.683</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_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>00:52.496</p></td>
+<td><p>00:52.995</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="deploy_classification.html#sphx-glr-topic-vta-tutorials-frontend-deploy-classification-py"><span class="std std-ref">Deploy Pretrained Vision Model from MxNet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_classification.py</span></code>)</p></td>
-<td><p>00:51.719</p></td>
+<td><p>00:49.688</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 955fc77b38..72c62a38b2 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>00:03.108</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.153</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>00:02.673</p></td>
+<td><p>00:02.714</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>00:00.440</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 efd5df7996..f18d2c6ab3 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>00:00.767</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.764</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>00:00.413</p></td>
+<td><p>00:00.408</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>00:00.354</p></td>
+<td><p>00:00.357</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 69b1f65178..a82efbb09e 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -491,9 +491,6 @@ trials, we can load the best schedule from the log file and apply it.</p>
 <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">sch</span></a><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">args</span></a> <span class="o">=</span> <a href="../reference/api/pyth [...]
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>*E
-</pre></div>
-</div>
 </div>
 <div class="section" id="inspecting-the-optimized-schedule">
 <h2>Inspecting the Optimized Schedule<a class="headerlink" href="#inspecting-the-optimized-schedule" title="Permalink to this headline">¶</a></h2>
@@ -580,7 +577,7 @@ operator fusion.</p>
 <span class="p">)</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 94.882 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 93.327 ms
 </pre></div>
 </div>
 </div>
@@ -654,7 +651,7 @@ 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  33.236 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  16.007 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 25734aaa9e..e99a416131 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -679,16 +679,16 @@ 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: 9.50/9.50       result: MeasureResult(costs=(0.028269254,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6169953346252441, timestamp=1668611249.245705) [(&#39;tile_y&#39;, [-1, 4]), (&#39;tile_x&#39;, [-1, 32])],None,52
-No: 2   GFLOPS: 10.05/10.05     result: MeasureResult(costs=(0.026706745799999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.9295623302459717, timestamp=1668611250.5821307)       [(&#39;tile_y&#39;, [-1, 16]), (&#39;tile_x&#39;, [-1, 128])],None,74
-No: 3   GFLOPS: 1.66/10.05      result: MeasureResult(costs=(0.161746875,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7350432872772217, timestamp=1668611254.0759397)        [(&#39;tile_y&#39;, [-1, 8]), (&#39;tile_x&#39;, [-1, 1])],None,3
-No: 4   GFLOPS: 3.68/10.05      result: MeasureResult(costs=(0.072891678,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3188543319702148, timestamp=1668611256.1606019)        [(&#39;tile_y&#39;, [-1, 128]), (&#39;tile_x&#39;, [-1, 16])],None,47
-No: 5   GFLOPS: 2.95/10.05      result: MeasureResult(costs=(0.09090782359999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6086602210998535, timestamp=1668611257.922664) [(&#39;tile_y&#39;, [-1, 2]), (&#39;tile_x&#39;, [-1, 8])],None,31
-No: 6   GFLOPS: 2.86/10.05      result: MeasureResult(costs=(0.0937155482,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6676971912384033, timestamp=1668611259.5862784)       [(&#39;tile_y&#39;, [-1, 2]), (&#39;tile_x&#39;, [-1, 16])],None,41
-No: 7   GFLOPS: 3.61/10.05      result: MeasureResult(costs=(0.07428857520000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3442738056182861, timestamp=1668611260.944852) [(&#39;tile_y&#39;, [-1, 8]), (&#39;tile_x&#39;, [-1, 8])],None,33
-No: 8   GFLOPS: 13.75/13.75     result: MeasureResult(costs=(0.0195251974,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5363571643829346, timestamp=1668611261.464481)        [(&#39;tile_y&#39;, [-1, 128]), (&#39;tile_x&#39;, [-1, 64])],None,67
-No: 9   GFLOPS: 9.56/13.75      result: MeasureResult(costs=(0.028064372200000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6169466972351074, timestamp=1668611262.2148101)       [(&#39;tile_y&#39;, [-1, 512]), (&#39;tile_x&#39;, [-1, 128])],None,79
-No: 10  GFLOPS: 13.15/13.75     result: MeasureResult(costs=(0.0204108224,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5056636333465576, timestamp=1668611262.7110298)       [(&#39;tile_y&#39;, [-1, 128]), (&#39;tile_x&#39;, [-1, 128])],None,77
+No: 1   GFLOPS: 11.03/11.03     result: MeasureResult(costs=(0.024329743600000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5313427448272705, timestamp=1668617045.4020307)       [(&#39;tile_y&#39;, [-1, 1]), (&#39;tile_x&#39;, [-1, 512])],None,90
+No: 2   GFLOPS: 12.24/12.24     result: MeasureResult(costs=(0.0219322012,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5325038433074951, timestamp=1668617046.6605668)       [(&#39;tile_y&#39;, [-1, 8]), (&#39;tile_x&#39;, [-1, 256])],None,83
+No: 3   GFLOPS: 14.66/14.66     result: MeasureResult(costs=(0.0183090816,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7388677597045898, timestamp=1668617047.8500664)       [(&#39;tile_y&#39;, [-1, 64]), (&#39;tile_x&#39;, [-1, 64])],None,66
+No: 4   GFLOPS: 12.39/14.66     result: MeasureResult(costs=(0.021670452599999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.4895329475402832, timestamp=1668617048.365852)        [(&#39;tile_y&#39;, [-1, 256]), (&#39;tile_x&#39;, [-1, 512])],None,98
+No: 5   GFLOPS: 8.70/14.66      result: MeasureResult(costs=(0.030850067400000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.8019249439239502, timestamp=1668617049.2892187)       [(&#39;tile_y&#39;, [-1, 16]), (&#39;tile_x&#39;, [-1, 64])],None,64
+No: 6   GFLOPS: 12.55/14.66     result: MeasureResult(costs=(0.021383448000000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5027682781219482, timestamp=1668617049.800311)        [(&#39;tile_y&#39;, [-1, 256]), (&#39;tile_x&#39;, [-1, 256])],None,88
+No: 7   GFLOPS: 12.11/14.66     result: MeasureResult(costs=(0.0221694228,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.593656063079834, timestamp=1668617051.070341) [(&#39;tile_y&#39;, [-1, 1]), (&#39;tile_x&#39;, [-1, 64])],None,60
+No: 8   GFLOPS: 4.03/14.66      result: MeasureResult(costs=(0.0666180478,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2662608623504639, timestamp=1668617052.3394432)       [(&#39;tile_y&#39;, [-1, 4]), (&#39;tile_x&#39;, [-1, 16])],None,42
+No: 9   GFLOPS: 13.09/14.66     result: MeasureResult(costs=(0.0205115432,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.4462544918060303, timestamp=1668617052.900465)        [(&#39;tile_y&#39;, [-1, 4]), (&#39;tile_x&#39;, [-1, 512])],None,92
+No: 10  GFLOPS: 1.71/14.66      result: MeasureResult(costs=(0.15705507219999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.621229410171509, timestamp=1668617055.5771248) [(&#39;tile_y&#39;, [-1, 512]), (&#39;tile_x&#39;, [-1, 4])],None,29
 </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 30f31c6c7b..3c17526836 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -560,7 +560,7 @@ 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;: 515.9832460300095, &#39;median&#39;: 516.074852450015, &#39;std&#39;: 2.1019770271666354}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{&#39;mean&#39;: 516.8028887700029, &#39;median&#39;: 516.7933151499938, &#39;std&#39;: 1.8442027952596247}
 </pre></div>
 </div>
 </div>
@@ -712,177 +712,178 @@ 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:   17.62/  17.62 GFLOPS | Progress: (4/20) | 9.23 s
-[Task  1/25]  Current/Best:   22.20/  22.93 GFLOPS | Progress: (8/20) | 11.31 s
-[Task  1/25]  Current/Best:    8.53/  22.93 GFLOPS | Progress: (12/20) | 14.39 s
-[Task  1/25]  Current/Best:   13.52/  22.93 GFLOPS | Progress: (16/20) | 16.87 s
-[Task  1/25]  Current/Best:    9.93/  22.93 GFLOPS | Progress: (20/20) | 19.27 s Done.
+[Task  1/25]  Current/Best:   14.83/  17.52 GFLOPS | Progress: (4/20) | 6.94 s
+[Task  1/25]  Current/Best:   22.90/  22.90 GFLOPS | Progress: (8/20) | 13.12 s
+[Task  1/25]  Current/Best:    5.64/  22.90 GFLOPS | Progress: (12/20) | 16.27 s
+[Task  1/25]  Current/Best:    5.76/  22.90 GFLOPS | Progress: (16/20) | 19.33 s
+[Task  1/25]  Current/Best:    5.27/  22.90 GFLOPS | Progress: (20/20) | 23.12 s Done.
 
 [Task  2/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  2/25]  Current/Best:   18.42/  19.63 GFLOPS | Progress: (4/20) | 2.67 s
-[Task  2/25]  Current/Best:   12.58/  19.63 GFLOPS | Progress: (8/20) | 3.74 s
-[Task  2/25]  Current/Best:   13.59/  19.63 GFLOPS | Progress: (12/20) | 5.36 s
-[Task  2/25]  Current/Best:    6.25/  19.63 GFLOPS | Progress: (16/20) | 7.11 s
-[Task  2/25]  Current/Best:   12.95/  20.04 GFLOPS | Progress: (20/20) | 8.42 s Done.
+[Task  2/25]  Current/Best:   21.38/  21.38 GFLOPS | Progress: (4/20) | 2.70 s
+[Task  2/25]  Current/Best:   13.71/  21.38 GFLOPS | Progress: (8/20) | 4.44 s
+[Task  2/25]  Current/Best:    7.99/  21.38 GFLOPS | Progress: (12/20) | 5.51 s
+[Task  2/25]  Current/Best:   13.04/  21.38 GFLOPS | Progress: (16/20) | 7.34 s
+[Task  2/25]  Current/Best:   12.92/  21.38 GFLOPS | Progress: (20/20) | 9.32 s Done.
 
 [Task  3/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  3/25]  Current/Best:   17.03/  17.03 GFLOPS | Progress: (4/20) | 3.31 s
-[Task  3/25]  Current/Best:    5.74/  20.14 GFLOPS | Progress: (8/20) | 5.95 s
-[Task  3/25]  Current/Best:   15.87/  23.62 GFLOPS | Progress: (12/20) | 8.30 s
-[Task  3/25]  Current/Best:   17.11/  23.62 GFLOPS | Progress: (16/20) | 10.95 s
-[Task  3/25]  Current/Best:   17.90/  23.62 GFLOPS | Progress: (20/20) | 13.52 s Done.
+[Task  3/25]  Current/Best:   10.70/  21.14 GFLOPS | Progress: (4/20) | 3.45 s
+[Task  3/25]  Current/Best:    6.22/  21.14 GFLOPS | Progress: (8/20) | 6.03 s
+[Task  3/25]  Current/Best:   15.77/  24.11 GFLOPS | Progress: (12/20) | 7.70 s
+[Task  3/25]  Current/Best:    7.64/  24.11 GFLOPS | Progress: (16/20) | 10.06 s
+[Task  3/25]  Current/Best:    5.62/  24.11 GFLOPS | Progress: (20/20) | 12.75 s Done.
 
 [Task  4/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  4/25]  Current/Best:    8.44/  18.73 GFLOPS | Progress: (4/20) | 3.59 s
-[Task  4/25]  Current/Best:    5.10/  18.73 GFLOPS | Progress: (8/20) | 11.01 s
-[Task  4/25]  Current/Best:   15.76/  18.73 GFLOPS | Progress: (12/20) | 12.91 s
-[Task  4/25]  Current/Best:   11.95/  18.73 GFLOPS | Progress: (16/20) | 14.61 s
-[Task  4/25]  Current/Best:   11.70/  18.73 GFLOPS | Progress: (20/20) | 17.29 s Done.
+[Task  4/25]  Current/Best:   16.29/  16.29 GFLOPS | Progress: (4/20) | 6.83 s
+[Task  4/25]  Current/Best:    7.81/  16.82 GFLOPS | Progress: (8/20) | 9.05 s
+[Task  4/25]  Current/Best:   11.80/  16.82 GFLOPS | Progress: (12/20) | 10.93 s
+[Task  4/25]  Current/Best:    8.10/  20.87 GFLOPS | Progress: (16/20) | 12.89 s
+[Task  4/25]  Current/Best:   10.30/  20.87 GFLOPS | Progress: (20/20) | 14.43 s Done.
 
 [Task  5/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  5/25]  Current/Best:    6.82/  19.14 GFLOPS | Progress: (4/20) | 3.05 s
-[Task  5/25]  Current/Best:    4.12/  19.14 GFLOPS | Progress: (8/20) | 4.96 s
-[Task  5/25]  Current/Best:   18.45/  19.14 GFLOPS | Progress: (12/20) | 6.41 s
-[Task  5/25]  Current/Best:    6.80/  19.14 GFLOPS | Progress: (16/20) | 8.18 s
-[Task  5/25]  Current/Best:    6.72/  19.14 GFLOPS | Progress: (20/20) | 10.05 s Done.
+[Task  5/25]  Current/Best:   16.87/  19.70 GFLOPS | Progress: (4/20) | 2.86 s
+[Task  5/25]  Current/Best:   15.38/  19.70 GFLOPS | Progress: (8/20) | 4.70 s
+[Task  5/25]  Current/Best:   20.58/  20.58 GFLOPS | Progress: (12/20) | 6.48 s
+[Task  5/25]  Current/Best:   18.06/  20.58 GFLOPS | Progress: (16/20) | 8.59 s
+[Task  5/25]  Current/Best:   13.01/  20.58 GFLOPS | Progress: (20/20) | 10.67 s Done.
 
 [Task  6/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  6/25]  Current/Best:   16.23/  16.23 GFLOPS | Progress: (4/20) | 4.04 s
-[Task  6/25]  Current/Best:   20.57/  20.57 GFLOPS | Progress: (8/20) | 5.80 s
-[Task  6/25]  Current/Best:   14.70/  20.57 GFLOPS | Progress: (12/20) | 8.75 s
-[Task  6/25]  Current/Best:   12.13/  20.57 GFLOPS | Progress: (16/20) | 11.07 s
-[Task  6/25]  Current/Best:   17.89/  20.57 GFLOPS | Progress: (20/20) | 12.82 s Done.
+[Task  6/25]  Current/Best:   14.33/  14.33 GFLOPS | Progress: (4/20) | 5.51 s
+[Task  6/25]  Current/Best:    4.06/  16.30 GFLOPS | Progress: (8/20) | 9.09 s
+[Task  6/25]  Current/Best:   13.88/  18.00 GFLOPS | Progress: (12/20) | 11.51 s
+[Task  6/25]  Current/Best:    5.40/  18.00 GFLOPS | Progress: (16/20) | 18.65 s
+[Task  6/25]  Current/Best:   18.29/  18.29 GFLOPS | Progress: (20/20) | 20.96 s Done.
 
 [Task  7/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  7/25]  Current/Best:   11.14/  16.33 GFLOPS | Progress: (4/20) | 4.95 s
-[Task  7/25]  Current/Best:   15.37/  16.66 GFLOPS | Progress: (8/20) | 6.95 s
-[Task  7/25]  Current/Best:   15.60/  16.66 GFLOPS | Progress: (12/20) | 9.50 s
-[Task  7/25]  Current/Best:   17.45/  17.45 GFLOPS | Progress: (16/20) | 12.01 s
-[Task  7/25]  Current/Best:   13.67/  20.09 GFLOPS | Progress: (20/20) | 13.81 s Done.
+[Task  7/25]  Current/Best:   15.20/  15.20 GFLOPS | Progress: (4/20) | 3.46 s
+[Task  7/25]  Current/Best:    6.23/  19.30 GFLOPS | Progress: (8/20) | 5.28 s
+[Task  7/25]  Current/Best:    5.76/  19.56 GFLOPS | Progress: (12/20) | 7.38 s
+[Task  7/25]  Current/Best:   12.47/  19.56 GFLOPS | Progress: (16/20) | 9.66 s
+[Task  7/25]  Current/Best:   12.35/  19.56 GFLOPS | Progress: (20/20) | 12.21 s Done.
 
 [Task  8/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  8/25]  Current/Best:    5.35/  15.05 GFLOPS | Progress: (4/20) | 4.50 s
-[Task  8/25]  Current/Best:   16.11/  16.11 GFLOPS | Progress: (8/20) | 15.62 s
-[Task  8/25]  Current/Best:    2.77/  16.70 GFLOPS | Progress: (12/20) | 21.04 s
-[Task  8/25]  Current/Best:   15.39/  16.70 GFLOPS | Progress: (16/20) | 28.78 s
-[Task  8/25]  Current/Best:   11.97/  16.70 GFLOPS | Progress: (20/20) | 31.86 s
+[Task  8/25]  Current/Best:   11.96/  17.28 GFLOPS | Progress: (4/20) | 4.86 s
+[Task  8/25]  Current/Best:   11.46/  17.28 GFLOPS | Progress: (8/20) | 12.13 s
+[Task  8/25]  Current/Best:    4.75/  17.28 GFLOPS | Progress: (12/20) | 18.56 s
+[Task  8/25]  Current/Best:   11.91/  17.37 GFLOPS | Progress: (16/20) | 21.37 s
+[Task  8/25]  Current/Best:    7.64/  17.37 GFLOPS | Progress: (20/20) | 25.35 s Done.
+
 [Task  9/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  9/25]  Current/Best:   13.79/  13.79 GFLOPS | Progress: (4/20) | 5.40 s
-[Task  9/25]  Current/Best:   10.91/  17.79 GFLOPS | Progress: (8/20) | 11.29 s
-[Task  9/25]  Current/Best:   12.27/  22.39 GFLOPS | Progress: (12/20) | 15.97 s
-[Task  9/25]  Current/Best:   10.27/  22.39 GFLOPS | Progress: (16/20) | 20.20 s
-[Task  9/25]  Current/Best:   17.87/  22.39 GFLOPS | Progress: (20/20) | 27.52 s Done.
+[Task  9/25]  Current/Best:    1.89/  12.86 GFLOPS | Progress: (4/20) | 3.63 s
+[Task  9/25]  Current/Best:   11.89/  16.17 GFLOPS | Progress: (8/20) | 5.42 s
+[Task  9/25]  Current/Best:   12.02/  16.17 GFLOPS | Progress: (12/20) | 10.23 s
+[Task  9/25]  Current/Best:   15.31/  17.52 GFLOPS | Progress: (16/20) | 12.62 s
+[Task  9/25]  Current/Best:   20.09/  20.09 GFLOPS | Progress: (20/20) | 14.54 s Done.
 
 [Task 10/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25]  Current/Best:   18.03/  19.55 GFLOPS | Progress: (4/20) | 2.93 s
-[Task 10/25]  Current/Best:    8.00/  19.55 GFLOPS | Progress: (8/20) | 4.37 s
-[Task 10/25]  Current/Best:   17.89/  19.55 GFLOPS | Progress: (12/20) | 6.14 s
-[Task 10/25]  Current/Best:    1.61/  19.55 GFLOPS | Progress: (16/20) | 8.15 s
-[Task 10/25]  Current/Best:    9.84/  19.55 GFLOPS | Progress: (20/20) | 11.03 s Done.
+[Task 10/25]  Current/Best:   14.32/  14.85 GFLOPS | Progress: (4/20) | 3.45 s
+[Task 10/25]  Current/Best:   11.53/  18.58 GFLOPS | Progress: (8/20) | 4.76 s
+[Task 10/25]  Current/Best:    8.58/  18.58 GFLOPS | Progress: (12/20) | 6.32 s
+[Task 10/25]  Current/Best:   14.22/  18.58 GFLOPS | Progress: (16/20) | 8.33 s
+[Task 10/25]  Current/Best:   11.08/  18.58 GFLOPS | Progress: (20/20) | 9.96 s Done.
 
 [Task 11/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25]  Current/Best:   18.43/  21.07 GFLOPS | Progress: (4/20) | 3.65 s
-[Task 11/25]  Current/Best:   17.97/  21.07 GFLOPS | Progress: (8/20) | 6.36 s
-[Task 11/25]  Current/Best:   18.34/  21.07 GFLOPS | Progress: (12/20) | 8.98 s
-[Task 11/25]  Current/Best:    6.28/  22.11 GFLOPS | Progress: (16/20) | 10.99 s
-[Task 11/25]  Current/Best:    8.99/  22.11 GFLOPS | Progress: (20/20) | 12.74 s Done.
+[Task 11/25]  Current/Best:    3.12/  17.00 GFLOPS | Progress: (4/20) | 4.80 s
+[Task 11/25]  Current/Best:   16.82/  18.12 GFLOPS | Progress: (8/20) | 7.19 s
+[Task 11/25]  Current/Best:   12.34/  18.12 GFLOPS | Progress: (12/20) | 10.09 s
+[Task 11/25]  Current/Best:    1.57/  18.12 GFLOPS | Progress: (16/20) | 13.71 s
+[Task 11/25]  Current/Best:   20.54/  20.54 GFLOPS | Progress: (20/20) | 16.01 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/  14.96 GFLOPS | Progress: (4/20) | 7.59 s
-[Task 12/25]  Current/Best:   13.11/  14.96 GFLOPS | Progress: (8/20) | 10.25 s
-[Task 12/25]  Current/Best:    7.19/  16.25 GFLOPS | Progress: (12/20) | 12.80 s
-[Task 12/25]  Current/Best:   13.40/  16.83 GFLOPS | Progress: (16/20) | 15.64 s
-[Task 12/25]  Current/Best:   18.27/  18.27 GFLOPS | Progress: (20/20) | 18.61 s Done.
+[Task 12/25]  Current/Best:    9.56/  15.70 GFLOPS | Progress: (4/20) | 10.39 s
+[Task 12/25]  Current/Best:   10.31/  18.76 GFLOPS | Progress: (8/20) | 12.35 s
+[Task 12/25]  Current/Best:   11.86/  18.76 GFLOPS | Progress: (12/20) | 17.78 s
+[Task 12/25]  Current/Best:    7.60/  18.76 GFLOPS | Progress: (16/20) | 24.01 s
+[Task 12/25]  Current/Best:   13.71/  18.76 GFLOPS | Progress: (20/20) | 26.60 s Done.
 
 [Task 13/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25]  Current/Best:   15.64/  20.70 GFLOPS | Progress: (4/20) | 3.65 s
-[Task 13/25]  Current/Best:    6.99/  20.70 GFLOPS | Progress: (8/20) | 7.70 s
-[Task 13/25]  Current/Best:   20.14/  20.70 GFLOPS | Progress: (12/20) | 9.74 s
-[Task 13/25]  Current/Best:   18.66/  20.70 GFLOPS | Progress: (16/20) | 12.46 s
-[Task 13/25]  Current/Best:   17.19/  20.70 GFLOPS | Progress: (20/20) | 14.71 s Done.
+[Task 13/25]  Current/Best:    5.12/  20.59 GFLOPS | Progress: (4/20) | 4.05 s
+[Task 13/25]  Current/Best:    6.12/  20.67 GFLOPS | Progress: (8/20) | 7.20 s
+[Task 13/25]  Current/Best:   12.08/  20.67 GFLOPS | Progress: (12/20) | 9.34 s
+[Task 13/25]  Current/Best:   14.34/  20.67 GFLOPS | Progress: (16/20) | 11.51 s
+[Task 13/25]  Current/Best:    9.25/  21.71 GFLOPS | Progress: (20/20) | 14.90 s Done.
 
 [Task 14/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25]  Current/Best:   15.95/  16.88 GFLOPS | Progress: (4/20) | 4.73 s
-[Task 14/25]  Current/Best:   10.84/  16.88 GFLOPS | Progress: (8/20) | 6.69 s
-[Task 14/25]  Current/Best:    4.59/  17.93 GFLOPS | Progress: (12/20) | 9.66 s
-[Task 14/25]  Current/Best:   16.22/  17.93 GFLOPS | Progress: (16/20) | 13.34 s
-[Task 14/25]  Current/Best:   13.15/  17.93 GFLOPS | Progress: (20/20) | 15.26 s Done.
-
+[Task 14/25]  Current/Best:    7.44/  11.29 GFLOPS | Progress: (4/20) | 6.25 s
+[Task 14/25]  Current/Best:   12.48/  12.48 GFLOPS | Progress: (8/20) | 8.62 s
+[Task 14/25]  Current/Best:   11.81/  13.03 GFLOPS | Progress: (12/20) | 13.01 s
+[Task 14/25]  Current/Best:   12.45/  13.03 GFLOPS | Progress: (16/20) | 18.03 s
+[Task 14/25]  Current/Best:   14.63/  14.63 GFLOPS | Progress: (20/20) | 23.32 s
 [Task 15/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25]  Current/Best:   19.42/  20.85 GFLOPS | Progress: (4/20) | 3.30 s
-[Task 15/25]  Current/Best:   12.02/  20.85 GFLOPS | Progress: (8/20) | 8.36 s Done.
-
-[Task 15/25]  Current/Best:   16.04/  20.85 GFLOPS | Progress: (12/20) | 10.34 s
-[Task 15/25]  Current/Best:   12.46/  20.85 GFLOPS | Progress: (16/20) | 15.89 s
-[Task 15/25]  Current/Best:   13.47/  21.22 GFLOPS | Progress: (20/20) | 17.92 s
+[Task 15/25]  Current/Best:   13.92/  16.77 GFLOPS | Progress: (4/20) | 3.48 s
+[Task 15/25]  Current/Best:   13.28/  19.09 GFLOPS | Progress: (8/20) | 5.91 s
+[Task 15/25]  Current/Best:   20.75/  20.75 GFLOPS | Progress: (12/20) | 7.20 s
+[Task 15/25]  Current/Best:   15.44/  20.75 GFLOPS | Progress: (16/20) | 9.49 s
+[Task 15/25]  Current/Best:   15.76/  20.75 GFLOPS | Progress: (20/20) | 10.71 s
 [Task 16/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25]  Current/Best:    8.65/  18.84 GFLOPS | Progress: (4/20) | 2.79 s
-[Task 16/25]  Current/Best:   15.93/  19.96 GFLOPS | Progress: (8/20) | 4.03 s
-[Task 16/25]  Current/Best:   15.47/  19.96 GFLOPS | Progress: (12/20) | 5.24 s
-[Task 16/25]  Current/Best:   18.49/  19.96 GFLOPS | Progress: (16/20) | 6.97 s
-[Task 16/25]  Current/Best:    6.75/  21.17 GFLOPS | Progress: (20/20) | 9.72 s Done.
+[Task 16/25]  Current/Best:    5.97/  14.01 GFLOPS | Progress: (4/20) | 3.62 s Done.
+ Done.
+
+[Task 16/25]  Current/Best:   15.54/  20.34 GFLOPS | Progress: (8/20) | 6.49 s
+[Task 16/25]  Current/Best:   19.30/  20.34 GFLOPS | Progress: (12/20) | 8.06 s
+[Task 16/25]  Current/Best:   14.24/  20.34 GFLOPS | Progress: (16/20) | 10.58 s
+[Task 16/25]  Current/Best:    4.57/  20.34 GFLOPS | Progress: (20/20) | 12.09 s Done.
 
 [Task 17/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25]  Current/Best:   10.18/  15.89 GFLOPS | Progress: (4/20) | 4.54 s
-[Task 17/25]  Current/Best:   20.77/  23.74 GFLOPS | Progress: (8/20) | 6.15 s
-[Task 17/25]  Current/Best:    9.72/  23.74 GFLOPS | Progress: (12/20) | 8.51 s
-[Task 17/25]  Current/Best:   17.01/  23.74 GFLOPS | Progress: (16/20) | 10.72 s
-[Task 17/25]  Current/Best:   10.42/  23.74 GFLOPS | Progress: (20/20) | 13.24 s Done.
+[Task 17/25]  Current/Best:   15.16/  18.26 GFLOPS | Progress: (4/20) | 3.45 s
+[Task 17/25]  Current/Best:   17.30/  20.30 GFLOPS | Progress: (8/20) | 5.45 s
+[Task 17/25]  Current/Best:   18.28/  20.30 GFLOPS | Progress: (12/20) | 7.76 s
+[Task 17/25]  Current/Best:   22.24/  22.24 GFLOPS | Progress: (16/20) | 9.28 s
+[Task 17/25]  Current/Best:   15.56/  22.24 GFLOPS | Progress: (20/20) | 11.75 s Done.
 
 [Task 18/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25]  Current/Best:   14.95/  19.22 GFLOPS | Progress: (4/20) | 4.99 s
-[Task 18/25]  Current/Best:   17.63/  19.22 GFLOPS | Progress: (8/20) | 6.65 s
-[Task 18/25]  Current/Best:    5.77/  19.22 GFLOPS | Progress: (12/20) | 13.28 s
-[Task 18/25]  Current/Best:    9.45/  19.22 GFLOPS | Progress: (16/20) | 17.04 s
-[Task 18/25]  Current/Best:   16.10/  19.22 GFLOPS | Progress: (20/20) | 19.12 s Done.
+[Task 18/25]  Current/Best:   15.15/  15.15 GFLOPS | Progress: (4/20) | 6.83 s
+[Task 18/25]  Current/Best:    9.94/  17.98 GFLOPS | Progress: (8/20) | 11.68 s
+[Task 18/25]  Current/Best:   10.07/  17.98 GFLOPS | Progress: (12/20) | 15.33 s
+[Task 18/25]  Current/Best:   11.48/  17.98 GFLOPS | Progress: (16/20) | 18.40 s
+[Task 18/25]  Current/Best:    5.07/  19.22 GFLOPS | Progress: (20/20) | 20.34 s Done.
 
 [Task 19/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25]  Current/Best:   13.38/  18.27 GFLOPS | Progress: (4/20) | 6.64 s
-[Task 19/25]  Current/Best:   19.57/  19.57 GFLOPS | Progress: (8/20) | 9.94 s
-[Task 19/25]  Current/Best:    2.68/  19.57 GFLOPS | Progress: (12/20) | 14.00 s
-[Task 19/25]  Current/Best:    8.18/  20.74 GFLOPS | Progress: (16/20) | 17.23 s
-[Task 19/25]  Current/Best:   10.09/  20.74 GFLOPS | Progress: (20/20) | 19.62 s Done.
+[Task 19/25]  Current/Best:    8.42/  21.05 GFLOPS | Progress: (4/20) | 6.45 s
+[Task 19/25]  Current/Best:   19.58/  21.05 GFLOPS | Progress: (8/20) | 9.99 s
+[Task 19/25]  Current/Best:   18.15/  21.05 GFLOPS | Progress: (12/20) | 12.09 s
+[Task 19/25]  Current/Best:   16.87/  21.05 GFLOPS | Progress: (16/20) | 15.33 s
+[Task 19/25]  Current/Best:    9.35/  21.05 GFLOPS | Progress: (20/20) | 19.20 s Done.
 
 [Task 20/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25]  Current/Best:    7.49/   7.49 GFLOPS | Progress: (4/20) | 3.45 s
-[Task 20/25]  Current/Best:   16.03/  16.76 GFLOPS | Progress: (8/20) | 9.41 s
-[Task 20/25]  Current/Best:    4.17/  16.76 GFLOPS | Progress: (12/20) | 12.24 s
-[Task 20/25]  Current/Best:   10.20/  16.76 GFLOPS | Progress: (16/20) | 14.23 s
-[Task 20/25]  Current/Best:    5.07/  16.76 GFLOPS | Progress: (20/20) | 17.55 s
-[Task 21/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25]  Current/Best:   10.31/  13.11 GFLOPS | Progress: (4/20) | 4.96 s Done.
- Done.
-
-[Task 21/25]  Current/Best:   14.77/  21.91 GFLOPS | Progress: (8/20) | 6.74 s
-[Task 21/25]  Current/Best:   12.92/  21.91 GFLOPS | Progress: (12/20) | 9.14 s
-[Task 21/25]  Current/Best:   15.33/  21.91 GFLOPS | Progress: (16/20) | 11.08 s
-[Task 21/25]  Current/Best:    8.90/  21.91 GFLOPS | Progress: (20/20) | 13.09 s
+[Task 20/25]  Current/Best:    9.72/  17.55 GFLOPS | Progress: (4/20) | 3.03 s
+[Task 20/25]  Current/Best:   13.98/  17.55 GFLOPS | Progress: (8/20) | 6.28 s
+[Task 20/25]  Current/Best:   10.40/  17.55 GFLOPS | Progress: (12/20) | 8.90 s
+[Task 20/25]  Current/Best:   17.84/  20.50 GFLOPS | Progress: (16/20) | 11.69 s
+[Task 20/25]  Current/Best:   15.56/  20.50 GFLOPS | Progress: (20/20) | 15.71 s
+[Task 21/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
+[Task 21/25]  Current/Best:    2.52/  12.52 GFLOPS | Progress: (4/20) | 3.34 s
+[Task 21/25]  Current/Best:   17.76/  17.76 GFLOPS | Progress: (8/20) | 7.84 s
+[Task 21/25]  Current/Best:    5.25/  17.76 GFLOPS | Progress: (12/20) | 9.86 s
+[Task 21/25]  Current/Best:    2.68/  21.66 GFLOPS | Progress: (16/20) | 12.26 s
+[Task 21/25]  Current/Best:   13.50/  21.66 GFLOPS | Progress: (20/20) | 13.87 s
 [Task 22/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25]  Current/Best:    4.44/   7.62 GFLOPS | Progress: (4/20) | 4.19 s
-[Task 22/25]  Current/Best:   14.70/  17.83 GFLOPS | Progress: (8/20) | 6.71 s
-[Task 22/25]  Current/Best:   12.40/  20.78 GFLOPS | Progress: (12/20) | 8.56 s
-[Task 22/25]  Current/Best:   20.28/  20.78 GFLOPS | Progress: (16/20) | 11.73 s
-[Task 22/25]  Current/Best:    7.02/  20.78 GFLOPS | Progress: (20/20) | 14.21 s Done.
+[Task 22/25]  Current/Best:    5.19/  12.99 GFLOPS | Progress: (4/20) | 3.85 s
+[Task 22/25]  Current/Best:    7.63/  16.16 GFLOPS | Progress: (8/20) | 5.67 s
+[Task 22/25]  Current/Best:    9.04/  18.37 GFLOPS | Progress: (12/20) | 8.13 s
+[Task 22/25]  Current/Best:   10.87/  18.37 GFLOPS | Progress: (16/20) | 11.44 s
+[Task 22/25]  Current/Best:    7.64/  18.37 GFLOPS | Progress: (20/20) | 13.54 s Done.
 
 [Task 23/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25]  Current/Best:    9.41/  19.74 GFLOPS | Progress: (4/20) | 4.17 s
-[Task 23/25]  Current/Best:    9.27/  19.74 GFLOPS | Progress: (8/20) | 6.75 s
-[Task 23/25]  Current/Best:   23.76/  23.76 GFLOPS | Progress: (12/20) | 8.81 s
-[Task 23/25]  Current/Best:    3.08/  23.76 GFLOPS | Progress: (16/20) | 11.64 s
-[Task 23/25]  Current/Best:   12.00/  23.76 GFLOPS | Progress: (20/20) | 14.27 s Done.
+[Task 23/25]  Current/Best:    1.55/  20.48 GFLOPS | Progress: (4/20) | 5.00 s
+[Task 23/25]  Current/Best:    5.36/  23.62 GFLOPS | Progress: (8/20) | 9.23 s
+[Task 23/25]  Current/Best:   11.24/  23.62 GFLOPS | Progress: (12/20) | 12.45 s
+[Task 23/25]  Current/Best:    8.43/  23.62 GFLOPS | Progress: (16/20) | 15.74 s
+[Task 23/25]  Current/Best:   11.42/  23.62 GFLOPS | Progress: (20/20) | 19.04 s Done.
 
 [Task 24/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25]  Current/Best:    2.27/   6.50 GFLOPS | Progress: (4/20) | 12.26 s
-[Task 24/25]  Current/Best:    7.90/   7.90 GFLOPS | Progress: (8/20) | 23.59 s
-[Task 24/25]  Current/Best:    6.66/   7.90 GFLOPS | Progress: (12/20) | 34.44 s
-[Task 24/25]  Current/Best:    8.96/   8.96 GFLOPS | Progress: (16/20) | 45.11 s
-[Task 24/25]  Current/Best:    7.19/   8.96 GFLOPS | Progress: (20/20) | 55.58 s
-[Task 25/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 25/25]  Current/Best:    9.06/   9.06 GFLOPS | Progress: (4/20) | 11.59 s
-[Task 25/25]  Current/Best:    3.50/   9.17 GFLOPS | Progress: (8/20) | 22.30 s
-[Task 25/25]  Current/Best:    7.17/   9.17 GFLOPS | Progress: (12/20) | 24.08 s
-[Task 25/25]  Current/Best:    7.55/   9.17 GFLOPS | Progress: (16/20) | 34.79 s
-[Task 25/25]  Current/Best:    4.37/   9.17 GFLOPS | Progress: (20/20) | 36.67 s
+[Task 24/25]  Current/Best:    5.51/   5.51 GFLOPS | Progress: (4/20) | 4.97 s
+[Task 24/25]  Current/Best:    3.99/   5.51 GFLOPS | Progress: (8/20) | 15.70 s
+[Task 24/25]  Current/Best:    3.49/   8.12 GFLOPS | Progress: (12/20) | 26.45 s
+[Task 24/25]  Current/Best:    6.96/   8.12 GFLOPS | Progress: (16/20) | 37.16 s
+[Task 24/25]  Current/Best:    1.07/   8.12 GFLOPS | Progress: (20/20) | 44.66 s
+[Task 25/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
+[Task 25/25]  Current/Best:    3.52/   5.27 GFLOPS | Progress: (4/20) | 2.61 s
+[Task 25/25]  Current/Best:    8.89/   8.89 GFLOPS | Progress: (8/20) | 13.29 s
+[Task 25/25]  Current/Best:    3.63/   8.92 GFLOPS | Progress: (12/20) | 24.01 s
+[Task 25/25]  Current/Best:    1.51/   8.92 GFLOPS | Progress: (16/20) | 26.99 s
+[Task 25/25]  Current/Best:    5.81/   8.92 GFLOPS | Progress: (20/20) | 28.02 s
 </pre></div>
 </div>
 <p>The output from this tuning process will look something like this:</p>
@@ -943,8 +944,8 @@ 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=0.621103
-class=&#39;n02123159 tiger cat&#39; with probability=0.356379
+<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
 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 +982,8 @@ 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;: 417.24817383000754, &#39;median&#39;: 416.0994904000063, &#39;std&#39;: 3.345817977638771}
-unoptimized: {&#39;mean&#39;: 515.9832460300095, &#39;median&#39;: 516.074852450015, &#39;std&#39;: 2.1019770271666354}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {&#39;mean&#39;: 410.15801464000106, &#39;median&#39;: 408.6431573000027, &#39;std&#39;: 3.983016703746832}
+unoptimized: {&#39;mean&#39;: 516.8028887700029, &#39;median&#39;: 516.7933151499938, &#39;std&#39;: 1.8442027952596247}
 </pre></div>
 </div>
 </div>
@@ -996,7 +997,7 @@ 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> ( 11 minutes  9.688 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes  53.937 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 3014416b7c..e20dacc976 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -537,7 +537,7 @@ 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>1.137e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.227e-07 secs/op
 </pre></div>
 </div>
 </div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index 154124a797..b6e4e44fa7 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -494,7 +494,7 @@ we can schedule the following series of operations ending with <code class="code
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sg</span><span class="o">.</span><span class="n">stages</span></a><span class="p">)</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x2134c3f0)), stage(b, placeholder(b, 0x21ee7aa0)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[ [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x22ef0670)), stage(b, placeholder(b, 0xe875ed0)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[i [...]
 </pre></div>
 </div>
 <p>We can test the correctness by comparing with <code class="code docutils literal notranslate"><span class="pre">numpy</span></code> result as follows</p>
diff --git a/docs/tutorial/sg_execution_times.html b/docs/tutorial/sg_execution_times.html
index 92311d214d..0083f04b08 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>14:44.179</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>14:03.663</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>11:09.688</p></td>
+<td><p>10:53.937</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>01:33.236</p></td>
+<td><p>01:16.007</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>01:02.680</p></td>
+<td><p>01:01.084</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>00:38.658</p></td>
+<td><p>00:35.950</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>00:18.300</p></td>
+<td><p>00:15.132</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>00:00.810</p></td>
+<td><p>00:00.771</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>00:00.644</p></td>
+<td><p>00:00.628</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>00:00.154</p></td>
+<td><p>00:00.145</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="introduction.html#sphx-glr-tutorial-introduction-py"><span class="std std-ref">Introduction</span></a> (<code class="docutils literal notranslate"><span class="pre">introduction.py</span></code>)</p></td>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index b61510d610..05128bf923 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -551,7 +551,7 @@ helper function to run a profile of the TVM generated code.</p>
 <span class="n">evaluate_addition</span><span class="p">(</span><span class="n">fadd</span><span class="p">,</span> <a href="../reference/api/python/target.html#tvm.target.Target" title="tvm.target.Target" class="sphx-glr-backref-module-tvm-target sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">tgt</span></a><span class="p">,</span> <span class="s2">&quot;naive&quot;</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#list" ti [...]
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000008
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000007
 naive: 0.000007
 </pre></div>
 </div>
@@ -600,7 +600,7 @@ 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: 0.000008
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallel: 0.000007
 </pre></div>
 </div>
 </div>
@@ -671,10 +671,10 @@ factor to be the number of threads on your CPU.</p>
 </pre></div>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator                  Timing             Performance
-   numpy    7.648709997738479e-06                    1.0
-   naive              6.6648e-06      0.8713626221899647
-parallel              8.3591e-06       1.092877099860181
-  vector    2.4603500000000003e-05     3.216686213397371
+   numpy    7.26831000065431e-06                     1.0
+   naive    6.705600000000001e-06     0.9225803521583898
+parallel              6.9417e-06      0.9550638318089201
+  vector             2.45513e-05      3.3778553746042523
 </pre></div>
 </div>
 <div class="admonition-code-specialization admonition">
@@ -990,7 +990,7 @@ 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: 0.018212
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018680
 </pre></div>
 </div>
 <p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -1031,7 +1031,7 @@ 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: 3.540408
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.420528
 </pre></div>
 </div>
 <p>Let’s take a look at the intermediate representation of the operator and
@@ -1095,7 +1095,7 @@ 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: 0.299061
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.298977
 </pre></div>
 </div>
 <p>By reordering the computation to take advantage of caching, you should see a
@@ -1153,7 +1153,7 @@ 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: 0.337274
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.333744
 @main = primfn(A_1: handle, B_1: handle, C_1: handle) -&gt; ()
   attr = {&quot;from_legacy_te_schedule&quot;: True, &quot;global_symbol&quot;: &quot;main&quot;, &quot;tir.noalias&quot;: True}
   buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1207,7 +1207,7 @@ 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: 0.118992
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.117542
 @main = primfn(A_1: handle, B_1: handle, C_1: handle) -&gt; ()
   attr = {&quot;from_legacy_te_schedule&quot;: True, &quot;global_symbol&quot;: &quot;main&quot;, &quot;tir.noalias&quot;: True}
   buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1282,7 +1282,7 @@ 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: 0.109797
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.108424
 @main = primfn(A_1: handle, B_1: handle, C_1: handle) -&gt; ()
   attr = {&quot;from_legacy_te_schedule&quot;: True, &quot;global_symbol&quot;: &quot;main&quot;, &quot;tir.noalias&quot;: True}
   buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1355,7 +1355,7 @@ 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: 0.110635
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.110747
 @main = primfn(A_1: handle, B_1: handle, C_1: handle) -&gt; ()
   attr = {&quot;from_legacy_te_schedule&quot;: True, &quot;global_symbol&quot;: &quot;main&quot;, &quot;tir.noalias&quot;: True}
   buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1421,7 +1421,7 @@ 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: 0.144369
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.146593
 @main = primfn(A_1: handle, B_1: handle, C_1: handle) -&gt; ()
   attr = {&quot;from_legacy_te_schedule&quot;: True, &quot;global_symbol&quot;: &quot;main&quot;, &quot;tir.noalias&quot;: True}
   buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1482,13 +1482,13 @@ 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      3.5404082826999996                     1.0
-        blocking     0.29906072260000005     0.08447068776257896
-   vectorization            0.3372738984      0.0952641253405912
-loop permutation     0.11899243670000001     0.03360980632698485
-   array packing     0.10979653869999999     0.03101239459768367
-   block caching             0.110635423    0.031249340235874376
- parallelization     0.14436925309999998    0.040777571842618265
+            none            3.4205275692                     1.0
+        blocking     0.29897708349999996     0.08740671649371484
+   vectorization             0.333743835     0.09757086538497238
+loop permutation            0.1175421273    0.034363742119316115
+   array packing     0.10842431959999999     0.03169812767372563
+   block caching     0.11074702389999999     0.03237717622778925
+ parallelization     0.14659330210000002    0.042856927516092366
 </pre></div>
 </div>
 <p>Note that the outputs on the web page reflect the running times on a
@@ -1520,7 +1520,7 @@ 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  2.680 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  1.084 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>